{"_id":"officeparser","_rev":"76-a273138361cf7d3c18904ee3c004f409","name":"officeparser","dist-tags":{"dev":"3.1.2","beta":"4.0.3","testPdf":"4.1.0","latest":"8.0.0"},"versions":{"1.0.0":{"name":"officeparser","version":"1.0.0","keywords":["office","docx","pptx","xlsx","parser","text"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.0.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"d90eb20fe55c3bae68d7e414ce2c99e46a4323c6","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.0.0.tgz","fileCount":4,"integrity":"sha512-CquE0IJ5PxcmdvsQa5GoS2hDbwcrmrqoIRGlBr/9W1QgasyrzoPSDumjaf1WqkePgwABhZ955EoVqsthd0UfWg==","signatures":[{"sig":"MEUCIQC4LnQ1dEF3BXs5Fa5teUiLoVtKmI5U3k4PCXhiG+HrSAIgapDRZcmcyEF5S5ATV17v9kqsbQ7X9TOQVr0ql/TIM0g=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":4307,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nD6yJ\r\n=npQJ\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"ae02079b1d37c8a65024be0be8e50ec8a0346097","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.0.0_1555324645848_0.9885368503744565","host":"s3://npm-registry-packages"}},"1.0.1":{"name":"officeparser","version":"1.0.1","keywords":["office","docx","pptx","xlsx","parser","text"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.0.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"a9147b74e3974cde5a021f52068489ed4bc77a32","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.0.1.tgz","fileCount":4,"integrity":"sha512-i8Vx9meF4NXOhRHwVGL3Sr8x0zi1kFobpvcVg4LBO9ZaPkDu6lz94dLZ9eqiQGgKJjiZADrePh64paEZwzfYBg==","signatures":[{"sig":"MEUCIDg8qk9llaxn18dwh1ZCH8xDClBAWo6Xxm9EyYuOkvqYAiEAitlclAM8in2Ly97caszAl4TvxSIQNwB3/oGcspiIOwI=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":4307,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\n7FbY\r\n=9f3Y\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"ee247ec35eeb18575ec8ce3649f4f9b23d5ec132","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.0.1_1555325231970_0.1238431152439805","host":"s3://npm-registry-packages"}},"1.1.0":{"name":"officeparser","version":"1.1.0","keywords":["office","docx","pptx","xlsx","parser","text"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.1.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"b911734721232702ce829025bf271892af47fe07","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.1.0.tgz","fileCount":4,"integrity":"sha512-B5XusaS2+2r/FeRK20M0kpQrVPhxnk2LLCeXbcDMRho38kbLCOQlxXlrcSokT+umXxQivndf2qLFW63IeZsBNw==","signatures":[{"sig":"MEUCIQC0jhWkToRfKN7/frUVPdm+R730h9hqea67yF8eo1RzEAIgZyA6iv90d+CqSL7FKXG74fxI+be59iqjaZnsqloAa2U=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":7350,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n\r\nwsFcBAEBCAAQBQJcuJP1CRA9TVsSAnZWagAAzIQP/iDpAfkIUh3VftkzLPTx\n81UTgKLqZxKq/SolYNeKcNpn7W3lo6/nRkOTu+bnYpcxGmyfqK531r2OAqGj\nFsTqKq5cFse6JNHSpvYIASYWy7CGOFB6g2NQamroGmd6aDCGu/5aeqBGmZsK\nMo6DEEXr3oRQ0DVjjk+tPcj50BhONvY0CR/L1wdB6hKGOzxM6pBwlJlEuV5W\nypkQQC/FDQIfp8o+xA0IA/DTlAJO1m3pDVtvTEmfcd3iG/NR4WElU5F6ve+u\nHAu1aY/MG6rpfBHHxNZ02Nhz8rdA0y/QMxJbLl+TMgk4G9rJhp8hLiA8bafl\ncZC/Tr44Omkjg0KUzIHMx+W98mzXpSoVuBoMfad2yIKJ8SvQ+98WLsXZkcIf\n7VOHAM9+6eDa48EMB3yhrkMzd9eIl6U59NrfBdXB5GSbkOVL4Rdngms0bWdB\nlQXd4siumVADjeCrVr/Z6KU+PL6UO+XJM+3E83ApjrNDp+1Rkig2GYtU2+Zn\nfz7Rw0iXxkmC38iwQHPpdTQAhe9G+3eXETeUJhODp+y8wtYqCPfPFrEJySlN\nv3vYJ2J1ogBgz/2jvy8F0WyE+JiP3TZQglFmhYFFZG+XmEW16V9pFa8g0Hnt\nqTWw/QVcyzqrRX6TMKpUy7uSdse7zSFEakO0P0S8+al2XnXwd4CUHhEm/fWG\n+hYa\r\n=JFsm\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"811fb8894dc0fae6a17fb7f90763907c1cdfa4d3","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.1.0_1555600372850_0.30903015714977267","host":"s3://npm-registry-packages"}},"1.1.1":{"name":"officeparser","version":"1.1.1","keywords":["office","docx","pptx","xlsx","parser","text"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.1.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"3d989a2bf7879c9ff534c673e8e556eba91d4c1f","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.1.1.tgz","fileCount":4,"integrity":"sha512-Vnvt4dpnX7cK6gddHgWc8bEcYHIzMosLThhjv4Fkl/rJCcvkpDs5Uw09oOD/htLepzAQ5C5JH00mypW9M942AA==","signatures":[{"sig":"MEQCIFZIBjyAniciHX4UdXvL1tp/IT/MK11QUCMYAtgNrfhzAiB5tsKLy6GR/SvMkKmDn6Ncz6Nwm3SHRO0WmiyYKs5B7w==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":7376,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nX5kr\r\n=HYHe\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"31e4dae72b5ada13d4abbc2966a6b5c83451bb0a","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.1.1_1555600726218_0.1744104394021675","host":"s3://npm-registry-packages"}},"1.1.2":{"name":"officeparser","version":"1.1.2","keywords":["office","docx","pptx","xlsx","parser","text"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.1.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"aa6cc9c52411de66b7793e70a0d3e22e9862e5c0","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.1.2.tgz","fileCount":4,"integrity":"sha512-39wUQEs9IvYUmGTeqVcW12R7XY+NS5U18NORblqCyQwCrYGnNOclKczOBhgMhIqXlWksf0fpauFKjJU84zabvg==","signatures":[{"sig":"MEQCIDZq2Rr3TmPoRtCYlW6J+GESjeB+s7uUk/T6SAxA3M7vAiBG/7KtwY67/OaABGAGkAlnSoMcqrjTFEQOcqpOfjq/3w==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":7407,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\n4At1\r\n=IfHC\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"94854c112518df3addecc6b2bd94ff56eb39248e","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.1.2_1555601300902_0.36091784465581633","host":"s3://npm-registry-packages"}},"1.2.0":{"name":"officeparser","version":"1.2.0","keywords":["office","docx","pptx","xlsx","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.2.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"d1994d90866defda1d21905eac22a6c9d0fb1744","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.2.0.tgz","fileCount":4,"integrity":"sha512-MnKpoXrstfRw2MeOUR1cQxZSjcx962Ou/jmntsSAOksEImVXkAbpWLP0VubsZoRExDKAVmfGfW/dIDGvGn5yng==","signatures":[{"sig":"MEUCIHWAfabgLYB8+L2kUvKucQew1H54VZlZclOK2UA0DD/NAiEAzUr6mtBceVjnY5UyJ2M+yzVnlF3vm4Ui95KlAX5u5Bs=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":13203,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nDIp/\r\n=JriY\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"a8f5fd6b0ada637344e78eaa693385f7e539da37","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.2.0_1555680968998_0.08723424672226443","host":"s3://npm-registry-packages"}},"1.2.1":{"name":"officeparser","version":"1.2.1","keywords":["office","docx","pptx","xlsx","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.2.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"aaf5a742c62d0d589ef0dfc9259c3651debdc3cd","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.2.1.tgz","fileCount":4,"integrity":"sha512-2bdh+KPoN4h0hN26K7UvkX1cH44M5HYa1abDn2JHvXaEschTMQFHlf4XVywGptZq6AA6MjAHxScx+Nzh+boaCg==","signatures":[{"sig":"MEQCIEqEw63pgbEzy1ZsxHlcHtRhN0LFnGDeIqk2Ck0xJvnLAiBz/oMXq+IqbZerh4peRrHiGfmT5vTxKiugChfCFvvE+A==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":14578,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\n4uC8\r\n=viKW\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"a0b037adc7b12f757082f200bd1846ca98852012","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"10.14.1","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.2.1_1555915355752_0.7982916722729474","host":"s3://npm-registry-packages"}},"1.3.0":{"name":"officeparser","version":"1.3.0","keywords":["office","docx","pptx","xlsx","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.3.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"72ec266cc9509434058350998523693285602211","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.3.0.tgz","fileCount":4,"integrity":"sha512-pAF3yMZaxsqO5k5kNfy6ZxOkvptA5vU7bB0KbJQ4pb487qBIkyNn5f3XpVDexM9by8M1COitunv1Hx4hLhd25g==","signatures":[{"sig":"MEUCIQCkqpXG/88fbFzJYozIRINd9ZOxSyz3se2KiujP3CNaygIgAZ7QhXBL17adRm+5f4letYol+3/MIF7hIeP2Dr8kToI=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":16841,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nG+uU\r\n=Nzhl\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"59f241f8f951b426aea057c5f46d451f6b613eea","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"10.14.1","dependencies":{"xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.3.0_1555925024890_0.4294544163035723","host":"s3://npm-registry-packages"}},"1.4.0":{"name":"officeparser","version":"1.4.0","keywords":["office","docx","pptx","xlsx","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.4.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"e364d851044b00a97052419fa46627f4988c749c","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.4.0.tgz","fileCount":4,"integrity":"sha512-ymHrSgA7ANzBkmATQHz6J36Fx9ccGF2SpbfbjF/BlWES0dw0aTGxIfpGC6WacTqYwgfhTbLgXhG+8BjV6rXWlA==","signatures":[{"sig":"MEUCIQDv1jb0XcB2EvdsM+BY8n7hGI6bEbx3lCAWE49g8PY3ZgIgfpWRUWcWFa7Y1xE6B132cGavdfDniJIrHMuJP1ejKgg=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":18132,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\naZQU\r\n=+cf3\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"554d58f6fbcdc67c59cdbde53cc71b98ae796991","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"10.14.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.4.0_1555983893888_0.8370097813549644","host":"s3://npm-registry-packages"}},"1.4.1":{"name":"officeparser","version":"1.4.1","keywords":["office","docx","pptx","xlsx","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@1.4.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"cd93b92e8b92e4b14f4c2650746ef38b9328f5ec","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-1.4.1.tgz","fileCount":4,"integrity":"sha512-rhbziFLztetPOOAHMgG9efsNmlVE9ZQxQFpkyhXXd8nVBhEEyFCgMFKeTPSNLd6DQrTJQM8ofUSvqJgaAuPd7A==","signatures":[{"sig":"MEQCICJTE93G2bX191EeSFlAm6xGAbzbgKHilc45blH4C/7jAiBX85fuBaYuEFnxTgnvpZ3ukjbp4/VYbUO5hjITHIh8CQ==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":18564,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nwM6Z\r\n=XKWt\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"56ccf635778eca7ecad18e9c15c7ab32f330e06f","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx and xlsx.","directories":{},"_nodeVersion":"10.14.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_1.4.1_1555984196736_0.4402672984616156","host":"s3://npm-registry-packages"}},"2.0.0":{"name":"officeparser","version":"2.0.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.0.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"1563ae34ef99661c52de5bf0ca4e691fa023537b","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.0.0.tgz","fileCount":4,"integrity":"sha512-tcw5fq9/ATQkZDl1R06fTSBLgFrdDbx3Jwx35SSwXfIbFQ/sx7czQQMPD0V4HhqQahqolGxEXb04ptowMh3KXA==","signatures":[{"sig":"MEUCIQDzN/GBoTzC5/s3bfZP6+XGwk02aXZfUfGTD3wv6HqqzQIgcZjzluBtBS7TRRwjrsaXEWI6xqUTZIDfYyO4E+IRUDc=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":21936,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nitNn\r\n=hwis\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"c43c73864e35dfb01905c1ab79c9ed5290987d64","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"10.14.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.0.0_1555988633484_0.1880583857100926","host":"s3://npm-registry-packages"}},"2.0.1":{"name":"officeparser","version":"2.0.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.0.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"4e38e02a0b3629fa058dce12683c9ed4363f3e1d","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.0.1.tgz","fileCount":4,"integrity":"sha512-4NP1hVhGGeJOaVoF11M+RBjfgOv1C1yaRjL7bsuirryf1pU4/N3wWk5Fw1gQpHgKuP3pDj2uMWmq5TApcjD22w==","signatures":[{"sig":"MEYCIQDcT10obDerRpQKWBI8GGeW2p5jP0o0e/RSeEFn32OVlAIhAMDytpfmgqC2E7tfWu/65f2bljd4EnK9wT4cn9Tfcsby","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":21936,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nEnPG\r\n=zjGu\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"8e8f275591ebb4ea5febad217be93d0e7f03b900","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.0.1_1556203944054_0.5916801514214831","host":"s3://npm-registry-packages"}},"2.0.2":{"name":"officeparser","version":"2.0.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.0.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"359398e80f4916e04052844bf17d03a15abf161a","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.0.2.tgz","fileCount":5,"integrity":"sha512-3P2reY9YccdpH3EWtbKT1qe9TSFxos/X8V7xiNvzDgnVaay5nHwfAnusnWY9/sYRmozjcKmUqCOdBqBaQreFQw==","signatures":[{"sig":"MEYCIQDgJTof9tCcp1hrV2wZy0tBMFXgZ6UUUbg3Jalam3SxsAIhALXyOKlBLLktOTmTRLrbi0b2R2LWfOStevIKdAEoofxO","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":24968,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nN198\r\n=/EWw\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"4243740a0c29b796d02c349cc1d27ee03df3c273","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"10.15.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.0.2_1556460433416_0.1221474013902899","host":"s3://npm-registry-packages"}},"2.0.3":{"name":"officeparser","version":"2.0.3","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.0.3","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"104642aaa33122fd6bb98eb478af7b16f00738db","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.0.3.tgz","fileCount":5,"integrity":"sha512-CV6QZxovO73SMdEU5dyYke71oDQuV6oRmFTuoG3zkhSWhS9Vjn6ogG3t7uolzUzENa1PlrSXSBV3Ik7n2X1H/A==","signatures":[{"sig":"MEYCIQD1UwSLMFC7NC2wb7bWs9kE7pXUD9/LtFoCSugfo/eJTAIhAMkW8gWX6Xfa9TnPnfCyaQidUSLCk1/wR49a7DtjIrAL","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":25113,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nrx7I\r\n=K5HS\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"b825e57a34a64ab58411e2bbe3a225fe3456dc33","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.4.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"10.15.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.0.3_1556629595019_0.031809271279741314","host":"s3://npm-registry-packages"}},"2.1.0":{"name":"officeparser","version":"2.1.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.1.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"1831f8f385e9eefd195a8cffd8fd5a8057e478d7","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.1.0.tgz","fileCount":5,"integrity":"sha512-Pg/+KiYwUdQID/p/oJ8VveV9739yfdIvGDVh6ATg6rnW0Lrfq4A+UhM2EJGtrELR6JDZkomNk45m0GKe3aicdw==","signatures":[{"sig":"MEUCIQCWN8VzbT1kLlB4/jI0rHuyLuoFVQTRbWDqa7QbRDsXCQIgfEItpqAltsqBdGzZrVStlMrQjHgpVxjMQ/ExYMEiFQE=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":27009,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nVNDe\r\n=VYeT\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"16e975296aebd3f388bcca27f1b5a4d841ab96e7","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.9.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.1.0_1560780049298_0.9242222828026658","host":"s3://npm-registry-packages"}},"2.1.1":{"name":"officeparser","version":"2.1.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.1.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"f264c623475f299cee8842e94c87584e80dca414","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.1.1.tgz","fileCount":5,"integrity":"sha512-8/gJ5zqwjt3Ruavmq37Tn4tML693NY1GcCWBj389MtMuEG48aXuS5Fpt/qKwh5yHNyoO34kUK1g41lND20uBmg==","signatures":[{"sig":"MEUCIQDOjujzrocNUFVFDLmKqBTYYMLRq8YsJ1rdSFSr/pN7RwIge08vZuT9vQnWTXoN+Z3UoKPqGkehiNbLkKnoQjvYIHE=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":27424,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\n/pWk\r\n=AdGW\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"525872db79d36c4919b57917a3dd6cc1248c79bc","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.9.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"8.11.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.1.1_1560780592614_0.8182037929563188","host":"s3://npm-registry-packages"}},"2.2.1":{"name":"officeparser","version":"2.2.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.2.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"97556f120e42ae9d5bf600f8d5d7642326aa0e8a","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.2.1.tgz","fileCount":6,"integrity":"sha512-ivsVuiFXjJ7EWKyRj9S5UmKQL2efwMPk8+378hZWM6KNfhKpxssl+lsEO4NdNpzx/vzc4zFmO2bC6ShsYRuMaQ==","signatures":[{"sig":"MEUCIQDGu35TLQcyvh/6awG5y6mJQuwdKqGDWtPBPCMFQbjH1AIgOfc+xGM75RVpBNnidAcFRDhvErQTT2BoE6BPfBmAWlE=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":31448,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n\r\nwsFcBAEBCAAQBQJe1JqZCRA9TVsSAnZWagAA4rYP/1GZb7yQM5c6WA7+4ncq\nNKNK46ZCh6iJV46H1vkL0M4DBaMw26PKj9hUlOpI6ih3sAg4sgF5/UYna/8L\nw0tk3eVd+K9bWi2+zWz66S+3CGLQ2IpeAgzS8/cW59flThB20YduawWfeSSC\njVZDqIbzfVqfIm98JrGh1fheJn25t52lhukWV+0QgUp8W5iPdSG2Bv9ZxYf3\nd5R4ECPBqBZKNX6qYp7eH7l9bfeLUiwnjCuHUh6EhNNvnVgHo2XqqTbxseIx\nXsfY+UckIUDUdvEYLooC4h0F83p60O+YMugsfF31en5GbrwiSxuO2PJE6Az1\ntpNcT/kUlxjNJcalLVLEzPYIzX0FEmb8Ps0B0IQQtG0eWkco0yBJxz3et18C\nPGuX4SnZ/n/y5QrIZHlSgZd6wcHV45JD0eeMggYZ5ghWqb2YL69hNKPe3VMM\ndgmrm5rI0sgsla6FxKbM2dyuWsbZY8wv2g4j66nBhLWFPhaxGtBimkOYbXJ7\nxc/epayj5U89PSw7flK0pjJC3KGsGcJcsBK39V44dPQ6FtCBk2hiR/Qit/q/\nb31bwK0tFnhfHfwWwqgjBsH6jz80YwQMdwTiu+ISG7wf1XNwQmttZP5RMcQ/\n9hTxzrEskav+1MKuQuhKQHgtff/T8f0sRyRgqJ5DjaC1tp4F7oRUovaE3Vo0\nd8N3\r\n=DohA\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"8bcdf53cf88c80546ec274ac9db695a14dbbaa62","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.14.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"12.16.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.2.1_1590991513245_0.870422094898913","host":"s3://npm-registry-packages"}},"2.2.2":{"name":"officeparser","version":"2.2.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.2.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"3058269fee2ea0ff5943eed039641ac0fde70eaa","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.2.2.tgz","fileCount":6,"integrity":"sha512-zhZOYK8ZtPxYKd6ppc6SEFGQYmsKj6EEXR+3vQG1L1uRPfbcXafWPzUSqbNmN3Xdd9v7GIM0Eflykialu70mzA==","signatures":[{"sig":"MEYCIQCUi164p9qVx3wOzKRkMnyzCRBDdEtQWXUSzm9BA5VLhwIhAL9gPGRSOEIEDxF2pEW9uiesB852UPHFIu9ikHa9bMlq","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":31436,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.4\r\nComment: https://openpgpjs.org\r\n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\nOhKy\r\n=sjhW\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"2253caa05024807f96e3c9db2eaacbd368721eb8","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.14.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"12.16.3","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.2.2_1590991660379_0.09866493563307333","host":"s3://npm-registry-packages"}},"2.3.0":{"name":"officeparser","version":"2.3.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@2.3.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"1b7f4402d456b765d608dc3f1a5e9e1d441e3fbb","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-2.3.0.tgz","fileCount":6,"integrity":"sha512-DqucJ5ajh7OZrEuqilqWIly+wdVoA+5AVo//CfbU9dNMSLQxXc+HoZ2Y4mgC1siCzYtN0Ho3GPqYTYGCspIK2g==","signatures":[{"sig":"MEUCIQDtj/Tyz5V3Rf0+IidxoeC6hOp51/FNCaRwXqYO5TOq8AIgJ/oh3BE6tl0dsZWeiZcldyHkCPFOulNEFwk2sfnAzdM=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":37742,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v3.0.13\r\nComment: https://openpgpjs.org\r\n\r\nwsFcBAEBCAAQBQJhmkr4CRA9TVsSAnZWagAAbaUP/0RitsQ0cJRr0x/RfS4Q\nI2uejmFTBbRk2fUBVBo8ypgp63zaQuXkxXy+L5iqRwBC2NGQN5MEXL4eNPOI\nhwRzhW82Gk2XVpAms121A7/1fi13mqSYz11ACEmQbM5PV/c42GK7pkJoyVKg\nBV9IlR0p54NjjZUgjWz5q9jpuPYjaENVT0jjs6PT3aPeV6zNPa/sndj3AU/G\ndDK5JJOftuupsi9DssHzTCBpq8amIW1GmjBX5wQ1TR1URcu0lAmqtW8cYwv1\npFUFjiDEa3ZsbDHp+aGl843Ip+UncF/Kef4H/S8fFzzH1Cn4kqayjgK5GtMZ\nRDPkI8eT/frHBspYiJEeSUoAKKAO/7hjOK7GiZuFRf8yixineieo4q1G9CNx\nCAMwLMyCH7E7QMtWCmuQnkR1jcgBTTxP8dcsr6gv+NA9PI3rQ9spzMnNUabe\n7SCoJqwzLsaGcQiNSzXw0yPCMHxM4XmEMucAwFECqQaOF6OTVtjUiYzz5Brk\njZBjzxEX4TALAIY2RR7bEFdrWRHOYKSS8otiLdlC/RkESgOzPl5C7jJvXRCw\ngsyirrlh4obWpsoTuZo0CRKrScOFTWc4JFDHLM8L/o/ZbaILk3bGSlItVpFh\ngFI9KIv3QxXVqFTWoiu0SPBcgkRc4u/cqfLCcNNcFE0KNEO1KdUaDGV1ck2a\n+KCs\r\n=ZVsr\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"6f8874a9aefae1d76095221d91dc78c9e8b3e96f","scripts":{"test":"echo \"Error: no test specified\" && exit 1"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"6.14.5","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"12.18.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_2.3.0_1637501688770_0.9514492681263245","host":"s3://npm-registry-packages"}},"3.0.0":{"name":"officeparser","version":"3.0.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.0.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"696086793e7d0311dce36aa0790c48fee9eb55b3","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.0.0.tgz","fileCount":20,"integrity":"sha512-M9ii3OyQkGhDTN9iYx3YWeQwowRQ7WcCcKTciKbZDuNd46iAm2dfgYpjQx/o1/OWF2Vx2n/QbEtp2bGXnb1jWw==","signatures":[{"sig":"MEQCICj/X5NarIXR6hFsziZmlUIPaw3UR4ldCXP4wRqzXhzNAiBvaigE917/NrctEL2CX4KQI/CofWIQreC/BgetIETPjA==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":2265771,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n\r\nwsFzBAEBCAAGBQJjk9DBACEJED1NWxICdlZqFiEECWMYAoorWMhJKdjhPU1b\r\nEgJ2VmrCJA//eZa77NqyYZM74KNvAvuujBuuPmgWWLRRlzlh7jm0rS6rOkUP\r\nMJSojLWBIFg/iWkGZAi+ybNsKjwFs11H89gHemZSS2+nGsnDzp50bjchhA+O\r\na6O8mx5PFvcsbIv+KuYOFK4HN0WpQZDx7Zi89vEysQOWlthE4/afm//NKCEH\r\nMimnEUwNGxFLBXBlVJekdtOMzZuOy989YorQQFNUH1/1C4wQktYfzIwXryXD\r\nykqEzeARc3T5dojgxD447QBWWJ7+mMeThliWIfInytV+OPSYutqKAGYgVWl7\r\nDKRvONdcodXl8IuOg6I5wBvWKyjGX5efPtHurWMclMe1n/R3dxpGrDBWvK/a\r\nOsV48gKDcooZS6k0DfvoRgHM7/l51f4j+oBE1YuRrp+KiAnmxF439oyXAXef\r\n4lTg7JW+wY/d+O3UnJbNRQwgdsHPyoc0Rk1QfFyLqXdFtNDOpTvmV94K6Y5l\r\n6Bok96oX1ygoZC9b83OVu51nICGRKFU4/8+QAlLxG4AH1vfKbyuycPWwrN/E\r\ng035OkUxEerJwbfDvh1gZ7M3ltWQk/BdM/vpj2Vre6KFQffb8APozmj/Y9Dt\r\nGj+VecXQ2C6rYfzYQuhlxs1kQffETpKJaAasjlpM9G2Qz1wCiDyqzQi+FhFg\r\nOXanoNdhOYOIAHNsJisoLtANUKgnsyx0IMA=\r\n=Dfu9\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"2fbd03c6aea53abce5569aa37fd61d0747632924","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"8.1.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"16.13.2","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.0.0_1670631617441_0.02384550948086539","host":"s3://npm-registry-packages"}},"3.1.0":{"name":"officeparser","version":"3.1.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.1.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"6e35d58cd76d4bdb3cb03e9832586d23259c5efe","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.1.0.tgz","fileCount":20,"integrity":"sha512-ajzFudxP7xIzvO7M+rTrpNyG9jRWAlCb3wCxPvJ7Yn4lFklacj95sic+9tAJenAixCoy9VGMsUI8S+LQAucliQ==","signatures":[{"sig":"MEQCIBDVRvAI0Gt0kffku+0rHYfR3fpblu8WzFRS+kRb/o6kAiBuW9g7voMKAnZXBcKxCwI3fGW4eQUpQXMMDJmgcR57Wg==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":2267116,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\nYV1tQPPDrZlrgzfVZlVW8GfD8B2yvpFVktM=\r\n=4b0+\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"2fbd03c6aea53abce5569aa37fd61d0747632924","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"8.19.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.12.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"readmeFilename":"README.md","_npmOperationalInternal":{"tmp":"tmp/officeparser_3.1.0_1671923179106_0.5230939223163236","host":"s3://npm-registry-packages"}},"3.1.1":{"name":"officeparser","version":"3.1.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.1.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"f8cfecdea46e94b5ab5410aa714397459af1a35e","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.1.1.tgz","fileCount":20,"integrity":"sha512-cjxwaeXZdkFPy/xkpARdNWixlgL4dY7pLwW+IP9tJoQnQcSykV79Tc4dMjMD0T4ZKfunA4tHoycijwCRceh85A==","signatures":[{"sig":"MEQCIHY5BJCaN/LZOXmkjO8WsUzmExr9biGQHgT7e+LDySqMAiBNdy4lHXJmh/mcGLGrDoMoovKaheNi3xvojeZpu+qwZg==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":2267137,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\n8OatCMhGZ0FOGLWokJDdO3kGU5wRQaKB7yY=\r\n=tiBV\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"125f9928d041f4c8e6ea3ef16027c32731026c6f","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"8.19.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.12.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"readmeFilename":"README.md","_npmOperationalInternal":{"tmp":"tmp/officeparser_3.1.1_1672212361950_0.05380275082018304","host":"s3://npm-registry-packages"}},"3.1.2":{"name":"officeparser","version":"3.1.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.1.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"7be311b82ac4d0fc659ba6db95c4af6742d02fe2","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.1.2.tgz","fileCount":20,"integrity":"sha512-fdNj7PlNYbM/sIxBDgw/eocy8VtzpNL646NqzYeGMOIYUbUw39tbSqxr2aBQFDTpnM/6HwDNgLdaQN6Nii/qbw==","signatures":[{"sig":"MEUCICaHD8oljNZtqwW456gkzHDYp3thjNgiC3gJ7a2gdYJQAiEA6SWH2ij7L4zvARBIDwCog/6KSrBR0uXzFQr4bMwfIjQ=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":2267165,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\nRd4kTnnJqxBwZAwxZnq7j17C0jLpGcMpZ6c=\r\n=Ogye\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"125f9928d041f4c8e6ea3ef16027c32731026c6f","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"8.19.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.12.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"readmeFilename":"README.md","_npmOperationalInternal":{"tmp":"tmp/officeparser_3.1.2_1672213109465_0.5310180277494245","host":"s3://npm-registry-packages"}},"3.1.3":{"name":"officeparser","version":"3.1.3","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.1.3","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"d867cd61b4c202e525753516157fd492450c579f","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.1.3.tgz","fileCount":20,"integrity":"sha512-hyrvWB+n5t5kk11vwtlm8e6nqm0UWhWg8TbQisbRX8Nv4HxvFak1j8I5t/LDPHLPrr3o1e51RJnInozdEy6Dfg==","signatures":[{"sig":"MEUCID/xuw+Av4SaYTz0OvOnN9bBLPtOE+Tm4RWIbW82X26CAiEAjsDY0ucmLP1PICxfT6PIdIatTZXKFnqkW+9Q2AldI24=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":2267113,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\n40h7aEuCEg6gyDO4uN084NFbBvZEJEFoi/U=\r\n=/jiM\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"54e4625741235875ab73611a8509af650c95a702","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"8.19.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.12.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.1.3_1672213455217_0.891932643005652","host":"s3://npm-registry-packages"}},"3.1.4":{"name":"officeparser","version":"3.1.4","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.1.4","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"7ef05f75fec8ee303c8d52f098d026bf04e60465","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.1.4.tgz","fileCount":20,"integrity":"sha512-uvBCdaqAiwUiDCzjlFvYyYc6k78wucjLtZJ/7JE2HMhVP2FdSWBB5Yf2b2Iamfc1UpppCRinxg7RsBqiC/nFHg==","signatures":[{"sig":"MEUCIQC0saGdrugbyOrm6LSXTi6XLA6GzpOz0quCjQ0yWWYZ5gIgAu8SYF2eHFYg2vKn2hHgJep7nqhHX5uXSZGRseHSzhA=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":2267113,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\nCqrebSU+7DyLzFTR6CGbmpcSAOX/mEInP0o=\r\n=f2Ag\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","gitHead":"3330f3f7362d7b747cee174301097b8e04d08ffe","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"8.19.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.12.1","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.1.4_1672213522030_0.04667488277242504","host":"s3://npm-registry-packages"}},"3.2.0":{"name":"officeparser","version":"3.2.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.2.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"24452396b0e51c3da2c036686cdf535495b5d352","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.2.0.tgz","fileCount":5,"integrity":"sha512-IYHKRxDsVOpVrc1UVpCbh7ScG8b+XTojqtyekJWBEuoSaPI4L0Pm7PEEdfTTwi7wPU8cnxPI6X9ozGHbjWUG5g==","signatures":[{"sig":"MEQCIGAtSK2PcElq1NQr2lEKKXLOcGltKLda1BfTTk/BtvHaAiA/QUjy2wti4ObyTa2mNGucAxEjk6LrTMlrB9aw9C9q2w==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":45239,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\nW5CJej10FF+g0b+iWH/0JbvvKp1LZwFuOA8=\r\n=Hsqy\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"3cf492fb787f13c5f75a3fecbbd7055202af088b","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.3.1","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.2.0_1680873962593_0.966451788660748","host":"s3://npm-registry-packages"}},"3.2.1":{"name":"officeparser","version":"3.2.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.2.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"6a6ce962fb6f780832be7c548196892faf47d07b","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.2.1.tgz","fileCount":5,"integrity":"sha512-FD4NkCvDDyHo1qvvWkSkjLEC59rsRcNYKT2NqNmTX3PZHvqZbLu1dXx/pKQZLotAmnbxQCF7IzWiLhXh90T0UQ==","signatures":[{"sig":"MEQCIDXQHjJSxGLITHugNsfulPEHc9QmCgVI4aX9MdCQ29LgAiB3pWJN2xOvqCxldvl/7YqFWHFHftkXzN3be/84J2AJzg==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":45392,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\nuisZ/XEiyz2aRKXJetjvd22cqBNwwCl3n8w=\r\n=mjv4\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"f06ef175aedc28319f21525db84ca63a92dd2d50","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.4.19","decompress":"^4.2.0"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.2.1_1681594058403_0.4782863047857866","host":"s3://npm-registry-packages"}},"3.2.2":{"name":"officeparser","version":"3.2.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.2.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"b9eb3bad05d784ce05a10ece4248267d732b2665","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.2.2.tgz","fileCount":5,"integrity":"sha512-3ZFtViRm6sOlHsG4JS01XTa7VLm6DcCJ68BSY66QylYTqO/5lvOW/I/qGMkAFyDS1SuoFz1jCWxySUWH4SFZFA==","signatures":[{"sig":"MEYCIQCXsPdv2BbdJo5g3StwuxEOdLo8pRoIqG+XswzJlF7YxgIhALqAAW/FsjwRG+gpXYk3TK0hdRaQR+4tUmSGgx9Ue6N6","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":45391,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\nbR3zho4s5U97ft0wW39Y8deQfWGvL3jtbO4=\r\n=NPl6\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"19de256842b535c586c1a58de1826cd9ed5d78f2","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.5.0","decompress":"^4.2.0"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.2.2_1681594518737_0.8947158486986986","host":"s3://npm-registry-packages"}},"3.3.0":{"name":"officeparser","version":"3.3.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@3.3.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"ecf7adb561d5e316e525ff76657084bc2513bb6d","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-3.3.0.tgz","fileCount":5,"integrity":"sha512-VIMORYfPxuEQYMGVzIsE13Bl8tLZNkpDsn8ajwuqDoc3gp7D2nM9SNfx+lIy68N21v+pvR4+HsFZ3ELrKN3RlA==","signatures":[{"sig":"MEUCIQCAXrFgbEncia+vlK7YNQAv7Q5XPLXinQF5NsFJIHl99QIgXsSzvj4vM0osaSw2Swvd7sTxGy+I/vmVeTIZgdrxSvI=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":48020,"npm-signature":"-----BEGIN PGP SIGNATURE-----\r\nVersion: OpenPGP.js v4.10.10\r\nComment: https://openpgpjs.org\r\n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\r\n6UG/o4ihMkMRX/b70mWHFmzyfTpV9MTAGvg=\r\n=OIJm\r\n-----END PGP SIGNATURE-----\r\n"},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"8754f08e4c6b433e6e57c44ec9a896d48fea2f9f","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp and ods files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","xml2js":"^0.5.0","file-type":"^16.5.4","decompress":"^4.2.0"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_3.3.0_1682541911504_0.9815339887336876","host":"s3://npm-registry-packages"}},"4.0.0":{"name":"officeparser","version":"4.0.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"2393d40b6e9a7e6378b670aa277c6ac0ee9cbe3c","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.0.tgz","fileCount":5,"integrity":"sha512-2sl+dPD2+du9d1b76EuH/Vro6mvsXlDq5ol11aDPGpa1kzvTH7P7RUpgnhld2WUKDu7ZmfNVtbO6FM3RVksm/A==","signatures":[{"sig":"MEUCIQC0hM95yAbqwCqLgicd021TFyzKM4SzhimtYNkeFQf23wIgB10dpA9PyN9Zs8F6DcrXBWMRX8xwiOWdAZnmrrCLgj0=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":44423},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"d5873bc12574bb7f047d0760ad2b6a640cdb6f78","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.2.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"21.0.0","dependencies":{"rimraf":"^2.6.3","xmldom":"^0.6.0","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.0_1698227888947_0.9410822565174","host":"s3://npm-registry-packages"}},"4.0.1":{"name":"officeparser","version":"4.0.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"e57d416b23bd0c7b26b4c3497d4a61e4a8fdb8f8","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.1.tgz","fileCount":5,"integrity":"sha512-rcSptSKHED4m/kj72h3yf+WtWQPQ6W6P94LOoh6aWZrqt8cNYgi2pQvihk/+I1q2+Uie/GDPFudn2MZQzIbKSg==","signatures":[{"sig":"MEYCIQCW3nwqX172FPHgCM0HchJGGG09cYuYsjdmcIrixCtARAIhAMb/Wfw/kJVcNK1w2qmyaesUnGaq1CJHadm+KyUOXzGy","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":44440},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"c8ac3ae364b5e949ccedc590531f23da68aefbeb","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.2.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"21.0.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.1_1698230111026_0.5060015170920138","host":"s3://npm-registry-packages"}},"4.0.2":{"name":"officeparser","version":"4.0.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"7b65544db7a36c96fedb5f8341aef06d4cce5194","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.2.tgz","fileCount":5,"integrity":"sha512-8qQD6mGQgbbjU77hO6tNnv2auwmYhQd8rger72Gq+e5utWDv5jCf5xoz517zNAg09+C9VahNsu+85+LA14qoag==","signatures":[{"sig":"MEYCIQD7MniDg11tz3euReT3oJ637nTrIgUkMQrdU2BdE4exCQIhANxd83EQY3DvQ0YJ6bXWGi6XP0OzxU8CQkwiKx0hHf29","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":44080},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"7159b91b9cd2a2dd041483e99a144bcceab0f5ab","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.2.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"21.0.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.2_1698235787903_0.9899312151965816","host":"s3://npm-registry-packages"}},"4.0.3":{"name":"officeparser","version":"4.0.3","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.3","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"1a97e7f70ce986839b9633ccbe10bde6fd1badfc","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.3.tgz","fileCount":5,"integrity":"sha512-3UJ9qlPkVT1eak9CW02rdtHz/V7UkagZKOAo0g6D9zEMjYQQt+tF4gT81rsRGu3tfE3AHyeDsu+XVpS8tTW6cw==","signatures":[{"sig":"MEQCIAI3A2a65H8wfQPzVqh4np/wsNj5guGXcgarScTfFglXAiAbwnHMAb8VbmB9EU3U9BsiZPAvqB30Eu1HQ89VnAplUA==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":44016},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"c968e4929a99c238f7d0741f7d1b349aff86b9a9","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.2.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"21.0.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.3_1698237968385_0.7209940739146026","host":"s3://npm-registry-packages"}},"4.0.4":{"name":"officeparser","version":"4.0.4","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.4","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"67b12b6b9b4a569deb835761679b21259a995fb8","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.4.tgz","fileCount":5,"integrity":"sha512-mkQaDZn7MbE6Jt9iA/0FXzwJz1TXZL+k+Xkx8yZfbIg4309Y6j5+Ctgrvt9KTCdQfXGcHzlZnlGmdrJuJzaacw==","signatures":[{"sig":"MEYCIQCWvPc2OGw9ALfAj9c+iR9hfFE9qDPth89ChwE55BddpgIhANjx+ub8S4BNdmqGYISPUor/UyQmdkbKGeStR7mCLKF7","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":44016},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"1ad0832227a490be7bb9b2278ba1572b17dfff38","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.2.0","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"21.0.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.4_1698238650676_0.06179310363260049","host":"s3://npm-registry-packages"}},"4.0.5":{"name":"officeparser","version":"4.0.5","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.5","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"61ad3eb81a436170efa29dbe1ea5937f0e90e619","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.5.tgz","fileCount":5,"integrity":"sha512-8uUuNCaafpHH5bF1uxLS0KxAzgN5KiX1K8GADqwCoebUJo8TlZR7EGEbJwdl5lG2OtDBJWNzujREkIM4fy5I3Q==","signatures":[{"sig":"MEUCIDYC6EKHxRd6DmLqjbWM/2RWIM60XIztKZFELrPUh2RsAiEAuaQw3uqOcTscdDuCOiyESzQ6nhPL1eUeKacxKNIOM/M=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":45850},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"e3c9b30ea5c87a4e8a8d37ba61155ba7efbb9f3c","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.5_1700943801746_0.17585535096187788","host":"s3://npm-registry-packages"}},"4.0.6":{"name":"officeparser","version":"4.0.6","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.6","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"41e8f056c9a4031f9d83da8f724f06690d7518d1","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.6.tgz","fileCount":5,"integrity":"sha512-VG5JWcXlbsXJotXj9cz5bZzq1YHK14lYwRBT36XW6Eu2/UUpr/8FQLIYfbnssj46E6zE4MjVVR3LDf+DkUMl0Q==","signatures":[{"sig":"MEYCIQDqln+IYe1fthHRP0E0W+uiH5HBUevDEdhVHuns4FZqAQIhALLojxgbGcmYiOXayhe64d9tRzTrhkJtTYH65QZQ1e5/","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":47347},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"e3e9827092fb39556dcfc439d79b8c854883e324","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.6_1704229229486_0.5914312337612964","host":"s3://npm-registry-packages"}},"4.0.7":{"name":"officeparser","version":"4.0.7","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.7","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"64d5856b371050f4df953a5dee6e38009155e655","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.7.tgz","fileCount":5,"integrity":"sha512-jyomy7y2/oqi3Xju5PKdON5rnONcg44WAbeh2fmOyHYIoMWgb9rrM00Vc5wzBd9xrVGJfI9GwcB2JIVhcjji/w==","signatures":[{"sig":"MEQCIHH8iknwOudnZ8edruvpX0uLMFFVzS3K2cF58Nh+YzgIAiAJtQLC4m4ZSdwK01sRwvSi7s7wAePIKg5F8+f7mHNiDg==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":47251},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"6a4d7ec0296d84712ed4a20c5a5bc0411654ac09","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.7_1707342381568_0.4925143920171633","host":"s3://npm-registry-packages"}},"4.0.8":{"name":"officeparser","version":"4.0.8","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.0.8","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"46def4a4664e8e2a36717bc5ae2bd99298eab565","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.0.8.tgz","fileCount":5,"integrity":"sha512-dIVwWkKWwFy7qQO+8foRTTDJybs3CEJORDulCQPqirqhtiK2cETojmuekRtBcVebpcAKCXTg4dYs0mjmifwJKA==","signatures":[{"sig":"MEYCIQDiXjfGaEs052Ymp3ALC/m2yYiqCv3HPysQf2AHPe08dQIhAJ8XcOJpUPHK+ILelpIqYPTiu8n9W58GvL4W97DAmyby","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":47252},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"55a3b701bfceaa6de6c3d2551021304563ff2c59","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","pdf-parse":"^1.1.1","decompress":"^4.2.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.0.8_1707689558288_0.03513138333649968","host":"s3://npm-registry-packages"}},"4.1.0":{"name":"officeparser","version":"4.1.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.1.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"907ecd2c8cbe29c12cb9b73c058ba3a26d719596","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.1.0.tgz","fileCount":9,"integrity":"sha512-dpkjpF39zxhzpdv2AhQx7lsWo3UEkwe/4/BNbGjtpWzYr+0PPSb9LN2sTlEnxY0iN0t4O06whX7ia9ORKv42Gg==","signatures":[{"sig":"MEQCIExPI9YzJlbTuEk2sgUcmOB5zTYJxrl48rJi/ZNT0r8PAiBg48zo3rqk9P/HaCU/rkdX8x2E3hajA/X/GB0P8qqNzg==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":6283564},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"55a3b701bfceaa6de6c3d2551021304563ff2c59","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","decompress":"^4.2.0","node-ensure":"^0.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"readmeFilename":"README.md","devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.1.0_1715020179025_0.4578597836706342","host":"s3://npm-registry-packages"}},"4.1.1":{"name":"officeparser","version":"4.1.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.1.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"5c08eb3158c0f8d6d85f12e1e6a95b54f590a677","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.1.1.tgz","fileCount":9,"integrity":"sha512-bOh7l6Bt/caeyU9t+9yGdQF2N30j8puR7PhXmSI/NqssHNnfnTLp1ehpBo4KuIMeOvzhr8mvkXHFpR2qhH1uhg==","signatures":[{"sig":"MEUCIGqGFb6aVHLD2DuG4UqlDSzQRRpgX8gjjuhRaDMXTCLuAiEA008MzQRwU1oUuWfkXW7yTarboSMg6hCL4EFeYN1vCrI=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":6283971},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"0733d9a7bd6fb7449e6a860347486c70cae6c5b0","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"9.6.4","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"18.13.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","decompress":"^4.2.0","node-ensure":"^0.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.1.1_1715022540260_0.15116770851958106","host":"s3://npm-registry-packages"}},"4.1.2":{"name":"officeparser","version":"4.1.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.1.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"7f925d025eb391f0a6fea80e121fe7d2013fc57e","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.1.2.tgz","fileCount":9,"integrity":"sha512-QWg9cwxOi7fQ0CPho39Rsu10JA4fmHA+mZuZljCIrMcjCrE9bLRDGxKUJMxg4FVaZWoUVW/9dQUyqIBaAFBXIQ==","signatures":[{"sig":"MEQCICfg566CG4RFeX1NpXbcpLo7WQmwwkEUFtKLGV0gurGfAiAzcPG8dl8woiutc1qXCeIQZCznxh2wUfY7Tb19LLsL/g==","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":6286956},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"4d21a6825e1355e6082c004cf5bf99f07182545d","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.17.0","dependencies":{"rimraf":"^2.6.3","file-type":"^16.5.4","decompress":"^4.2.0","node-ensure":"^0.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.1.2_1728851033754_0.8509603586079246","host":"s3://npm-registry-packages"}},"4.2.0":{"name":"officeparser","version":"4.2.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@4.2.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"6d0baf411bd21e7e31a4b1f206af7034a4506ca2","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-4.2.0.tgz","fileCount":9,"integrity":"sha512-LXSfaET8ZOBNjmSev4K1N6AiKTaY7m9NkddeCaMUdEe5D/HUuv2byB8VoPIaiLldtKun0I92tbhO+VGDUr/aXQ==","signatures":[{"sig":"MEUCIQCxXm+eSxWG07Y2VbpvRA9hjNSn6sMSbVg2ipZSw0LWjQIgfb/u2D2VaUD1VgBBae4DkjIx5w3wJhbdSssw6zYG7WA=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":6289467},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"969f6b6458190d496b51643f2ebb1f64329db871","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.17.0","dependencies":{"rimraf":"^5.0.10","file-type":"^16.5.4","decompress":"^4.2.1","node-ensure":"^0.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/xmldom":"^0.1.33","@types/decompress":"^4.2.6"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_4.2.0_1728946215820_0.37022348834148144","host":"s3://npm-registry-packages"}},"5.0.0":{"name":"officeparser","version":"5.0.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@5.0.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"b36496d9bf3014d79c68c476669c87a0c24c66cf","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-5.0.0.tgz","fileCount":9,"integrity":"sha512-IpUOA2yEBgmOH7gwekzg5V6dSzi3p3Tn98f88Hk1KneG1Q7hZ+bZXbpAPqDc1F02r192joIZAZw9Wd0PT0NwRg==","signatures":[{"sig":"MEUCIEKTFw6XCm/TQCVF3YLjditd83tpzarIhLt37v67KNnlAiEA062sWvc4C3R7zeT2nnqRm294zIl0of8EJXEvkoyH2zg=","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":6289747},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"ed19851f1998d986193f159829a0730b7e88ad99","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.17.0","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","node-ensure":"^0.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_5.0.0_1729544172193_0.4254913546068375","host":"s3://npm-registry-packages"}},"5.1.1":{"name":"officeparser","version":"5.1.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@5.1.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"5d28fd33cc094f42c1ce1a69cd5d29946d6a6eed","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-5.1.1.tgz","fileCount":9,"integrity":"sha512-trBCPmYQDFUCmch6YBxHhMFkDyhTl+vG8PDQHPOwRyeCDKnrrKpph2W7og7hg5T5RRF0yeyaOMasN7GZWbYuCA==","signatures":[{"sig":"MEYCIQDArMAWsdEIvYrIZY+tAcWPCLTuK/bciqqhfyAf7Se2RwIhAJDYaQZkf0m+Gv4zFxnhwhfYPAdbUayPph9yI4a9jDqd","keyid":"SHA256:jl3bwswu80PjjokCgh0o2w5c2U4LhQAE57gj9cz1kzA"}],"unpackedSize":6291801},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"c969c7ae1d4dc66c65eb2f5345b9d849fd309a09","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.18.0","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","node-ensure":"^0.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_5.1.1_1731368513916_0.0852867093845655","host":"s3://npm-registry-packages"}},"5.2.0":{"name":"officeparser","version":"5.2.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@5.2.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"92049291a06a76620dd927993a5e064e328bf747","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-5.2.0.tgz","fileCount":5,"integrity":"sha512-EGdHj4RgP5FtyTHsqgDz2ZXkV2q2o2Ktwk4ogHpVcRT1+udwb3pRLfmlNO9ZMDZtDhJz5qNIUAs/+ItrUWoHiQ==","signatures":[{"sig":"MEYCIQD9I35N4My6LE36cUmYcere5kphPmqFRt9cX0LTJmYj7wIhAN2NIhOXH59J7xicr/WDW+YBtq2IBX95A02dsPzRpjhh","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":57806},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"74cf227724624db0587a0379918e78abac46af10","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","actor":{"name":"harshankur","type":"user","email":"harshankur@outlook.com"},"email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"^5.3.31","node-ensure":"^0.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_5.2.0_1751745846112_0.41769939968204484","host":"s3://npm-registry-packages-npm-production"}},"5.2.1":{"name":"officeparser","version":"5.2.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@5.2.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"b085ba03d166b89993d36ca57c08f871959f1c2c","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-5.2.1.tgz","fileCount":5,"integrity":"sha512-APK7/nlaeW3Q/HmzphazVlyktLoi2VfnBd8rrV1JptJuNpD6HtJIWw4h+c2pnlu1wp+ZyBjPxDFcHbC+3NUOpA==","signatures":[{"sig":"MEUCIQDKXD5D3DKfqGpuQ2hnru/I9UfGyVqzQDWw3AZJWieuPwIgBxoQVXPW7XTfyMnQer6L/kebbi/CfJMJF7Z1V1gs+fY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":57915},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"d188e82a4233df50c6e7fbfabae68e49eb84436f","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.19.5","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"^5.3.31","node-ensure":"^0.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_5.2.1_1759181186416_0.1031395497509402","host":"s3://npm-registry-packages-npm-production"}},"5.2.2":{"name":"officeparser","version":"5.2.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","parser","text","extract text","document","word","excel","worksheet","powerpoint","slides"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@5.2.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"officeParser.js"},"dist":{"shasum":"75efff96424f97787af0d3fa0bafe2b63832a418","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-5.2.2.tgz","fileCount":5,"integrity":"sha512-5JrV1CZFqTv/27fXy2bcf+3g6BpDZiJ3XoSRW3fb2i2EFex0DduqjTxiU2RsJ08WBsk4Hp0nZoGi9ZtHMZFaPA==","signatures":[{"sig":"MEUCIA0VeOHAdbkA5dZjSPukhdVgzufel5ea0FAjPgE9FM6YAiEArDdtwM+rsRwm+g6qIy49IwJUSoxITAkWdxQn2w8h5BA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":58739},"main":"officeParser.js","types":"typings/officeParser.d.ts","gitHead":"269b5029f47c18dfa84704a3736abdac50eb6a8a","scripts":{"test":"node test/testOfficeParser.js"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.8.2","description":"A Node.js library to parse text out of any office file. Currently supports docx, pptx, xlsx, odt, odp, ods, pdf files.","directories":{},"_nodeVersion":"20.19.5","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"^5.3.31","node-ensure":"^0.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_5.2.2_1762949083679_0.6010803314154973","host":"s3://npm-registry-packages-npm-production"}},"6.0.1":{"name":"officeparser","version":"6.0.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.0.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/index.js"},"dist":{"shasum":"38cfc05326b6ebfd0a83f735f72462e2a9c08890","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.0.1.tgz","fileCount":35,"integrity":"sha512-wAirc/zYhT2DgkDVOrl5Gs9jxUB7NRbZwd27jqnBgogSyswoR/gritiqMKPOoIBumBlUCktlmjGXxWUivBT9Dw==","signatures":[{"sig":"MEYCIQCiyIbGilEST9wvUPcaqyECljD0os3u+Ur71OlWgbkFOgIhAO+3UQjLn0KXsyTeoitLAjl3xBlwcZJNrsUUwX51zBUm","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":9260564},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"6fac1a8bf52616c0c578dcc0bdfb8e345670c12b","scripts":{"test":"npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts","build":"tsc && node build_browser.js && npm run sync:docs","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","build:browser":"node build_browser.js && npm run sync:docs","prepublishOnly":"npm run build"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.9.2","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"22.16.0","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"5.4.530","tesseract.js":"^6.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","esbuild":"^0.27.0","typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3","esbuild-plugin-polyfill-node":"^0.3.0"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.0.1_1767366200895_0.32517092728963637","host":"s3://npm-registry-packages-npm-production"}},"6.0.2":{"name":"officeparser","version":"6.0.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.0.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/index.js"},"dist":{"shasum":"84c50446937366881acf8d0df95c43f08c73c9f4","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.0.2.tgz","fileCount":35,"integrity":"sha512-ePboPR7k+pyzlyMpxAXegnnsgZ2bao3BwhkM/oLvpCqt94kJLGj3EXg1jZGGq5u6PUwU7BwSlefuvNcza0aSLw==","signatures":[{"sig":"MEUCICe2R6p22v8aXKm0s/yOlc7fghKCfR6r+uADZ65K7TzxAiEA1IIGQRvO6Z9Qml3HpFxnJ1VozBu/3+HddQy549l4OQc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":6674197},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"db1676042935a24fa3eeaff1295e06443c093570","scripts":{"test":"npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts","build":"tsc && node build_browser.js && npm run sync:docs","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","build:browser":"node build_browser.js && npm run sync:docs","prepublishOnly":"npm run build"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.9.2","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"22.16.0","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"5.4.530","tesseract.js":"^6.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","esbuild":"^0.27.0","typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3","esbuild-plugin-polyfill-node":"^0.3.0"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.0.2_1767874643838_0.04068083676410472","host":"s3://npm-registry-packages-npm-production"}},"6.0.3":{"name":"officeparser","version":"6.0.3","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.0.3","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://github.com/harshankur/officeParser#readme","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/index.js"},"dist":{"shasum":"e7f393a523a30ca2a3102155948ab93e73c9f210","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.0.3.tgz","fileCount":35,"integrity":"sha512-I+r9o6dwb0Zn9pJZSRg+9o82f7k3yC0XY/TAl5q2g/3Lta/pzzYtIscWDvrgG3FEHg1jbfHcWvriBb0GQRFBqg==","signatures":[{"sig":"MEUCIA0V6Vtpv5T0ilql9Rga3GUqAImQTv3QEBKwa4W9pvfvAiEAgohqCGeRTBatCnQ1j+f9RZVs3rA5Qbdc3zK8aJh3H+Q=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":6680369},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"cdc6f1417e6d1c5e2e778b75c5e7adda8fccac45","scripts":{"test":"npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts","build":"tsc && node build_browser.js && npm run sync:docs","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","build:browser":"node build_browser.js && npm run sync:docs","prepublishOnly":"npm run build"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.9.2","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"22.16.0","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"5.4.530","tesseract.js":"^6.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","esbuild":"^0.27.0","typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3","esbuild-plugin-polyfill-node":"^0.3.0"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.0.3_1768056409570_0.141679565343388","host":"s3://npm-registry-packages-npm-production"}},"6.0.4":{"name":"officeparser","version":"6.0.4","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.0.4","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://harshankur.github.io/officeParser/","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/index.js"},"dist":{"shasum":"b39730dc705f64fd7ece8ce1ce6b8bcfacf43758","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.0.4.tgz","fileCount":35,"integrity":"sha512-zmxst4xbrUxCCY6w5BLmmtewJY5eHkLKNJ+2Z5OKY0JPh5qmtUSslFkg0fC3xc+0RG4DFdfQ36107B99yLMfuQ==","signatures":[{"sig":"MEUCIQDdvxen23GjnihiJwi9KAnTT2gbaEdj0WuNKloCQ/uJ8wIgZZJS71X8J6hN0Z0IqYuE0HNku3qZ1tEXIDD7ZIjbqeY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":6680362},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"0a980bf0a56d13181d439e97f07ed3f3c273c2b0","scripts":{"test":"npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts","build":"tsc && node build_browser.js && npm run sync:docs","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","build:browser":"node build_browser.js && npm run sync:docs","prepublishOnly":"npm run build"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.9.2","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"22.16.0","dependencies":{"yauzl":"^3.1.3","file-type":"^16.5.4","pdfjs-dist":"5.4.530","tesseract.js":"^6.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.10"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","esbuild":"^0.27.0","typescript":"^5.0.3","@types/node":"^18.16.1","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.33","@types/concat-stream":"^2.0.3","esbuild-plugin-polyfill-node":"^0.3.0"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.0.4_1768059235190_0.3866017407729996","host":"s3://npm-registry-packages-npm-production"}},"6.0.6":{"name":"officeparser","version":"6.0.6","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.0.6","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://harshankur.github.io/officeParser/","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/index.js"},"dist":{"shasum":"2dfd1579729ec3055860ec9ce6e246003a94c72f","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.0.6.tgz","fileCount":37,"integrity":"sha512-k6234uAYUCI98KYOiC7o/04FF1k2O/jlmxGQXS/sApN+f0lVnS6pGfgIS13DFg0e36oeM7Tb6URy/rHgPUdhsg==","signatures":[{"sig":"MEUCIQC8Z7NzSUPcS0q1G85rcc33xqj1ePl+ePkK7Miy6izudgIgKTXYbusCVv0IG21YGbudLG0N4bnGmMkkEFStT3pJhC0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":6734843},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"b8297e7f7e89f18ef62354d7137a15e3a3a734f8","scripts":{"test":"npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts","build":"npm run sync:versions && npm run build:node && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","prepublishOnly":"npm run build"},"_npmUser":{"name":"harshankur","email":"harshankur@outlook.com"},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"10.9.2","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"22.16.0","dependencies":{"yauzl":"^3.2.1","file-type":"^19.6.0","pdfjs-dist":"^5.5.207","tesseract.js":"^7.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.11"},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","esbuild":"^0.27.4","typescript":"^5.9.3","@types/node":"^22.13.10","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.34","@types/concat-stream":"^2.0.3","esbuild-plugin-polyfill-node":"^0.3.0"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.0.6_1774309213098_0.7662658270812481","host":"s3://npm-registry-packages-npm-production"}},"6.0.7":{"name":"officeparser","version":"6.0.7","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.0.7","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/index.js"},"dist":{"shasum":"04d5a9f6107c0421eb76591b40234398cdc57d98","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.0.7.tgz","fileCount":38,"integrity":"sha512-MkNHyWIfEZRDtB8c0fgJHdb4Ui0I/WztBjlUjlPiEbTO6dIYaJMt+llS5p5Foj13guUZgGxkkM9VwsVRthHNAA==","signatures":[{"sig":"MEQCIDKm30ODcLQaYX3PF6OeNFN+g7WGxlslDuyOZEnvs27zAiBXf69FWG++DKIYKhSLyLei4nJ8cpSGa05PTb7cMc86hg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@6.0.7","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2969396},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"gitHead":"1f1238c8abbce562bd209d0b70095115c775a1cd","scripts":{"test":"npm run test:clean && npm run build && npx tsx test/testOfficeParser.ts","build":"npm run sync:versions && npm run build:node && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.js docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","prepublishOnly":"npm run build","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.9.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"24.14.0","dependencies":{"yauzl":"^3.2.1","file-type":"^21.3.4","pdfjs-dist":"^5.5.207","tesseract.js":"^7.0.0","concat-stream":"^2.0.0","@xmldom/xmldom":"^0.8.11"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","esbuild":"^0.27.4","typescript":"^6.0.2","@types/node":"^22.15.5","@types/yauzl":"^2.10.3","@types/xmldom":"^0.1.34","@types/concat-stream":"^2.0.3","dts-bundle-generator":"^9.5.1","esbuild-plugin-polyfill-node":"^0.3.0"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.0.7_1774351956390_0.8087202064638701","host":"s3://npm-registry-packages-npm-production"}},"6.1.0":{"name":"officeparser","version":"6.1.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.1.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"131b0296353732de6f046a0fc194005a3c18b2d8","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.1.0.tgz","fileCount":46,"integrity":"sha512-S/dMjUyhbeyDNUjnuGKsmuDx3IoOTcyy6uFzZ6321paaF5NVQVS+Ht8SkQEzEQ85DJ256LnTroMTP2PVKebX1Q==","signatures":[{"sig":"MEYCIQCd/mh8QZF2GMwndm/T9fajiqc5zlCS9HWkK2gNemkVbQIhAKKla2GA/8wWhj06fklpPxuANRKekEs4EJ6Dg7S/s0Iu","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@6.1.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2028418},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"24b2e967d115aaa42755a41b17ec8b24266d750d","scripts":{"sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","test:parser":"npx tsx test/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.11.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"24.14.1","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.9"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","esbuild":"^0.27.4","process":"^0.11.10","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.1.0_1776175776797_0.5256715467706599","host":"s3://npm-registry-packages-npm-production"}},"6.1.1":{"name":"officeparser","version":"6.1.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@6.1.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"9452c6c4c336358ec1040b0a6b55be069485ceb5","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-6.1.1.tgz","fileCount":46,"integrity":"sha512-C8XcY7h/4It+ZZDTnPs9p7v2c09zcJUVQKZH4Q8ZtBLeVrauSSrJvvV8Orcq8fSJjxPFuQAueQqkqTfGv3HlPw==","signatures":[{"sig":"MEUCIQCY7xYpTGqqMQ94rnGcvibj5rm466aliT4tVVpbKH9TsgIgDXeI9PEnO8ERkhl8ZCKIEfgyl6a+7mDq7TiDMiUkbj0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@6.1.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2054459},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"a485286ceed31d827dc0f0c4ee902cad60864fab","scripts":{"sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results","test:parser":"npx tsx test/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.11.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf) into structured AST with rich metadata, formatting, and attachment support.","directories":{},"sideEffects":false,"_nodeVersion":"24.14.1","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","esbuild":"^0.27.4","process":"^0.11.10","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"_npmOperationalInternal":{"tmp":"tmp/officeparser_6.1.1_1777414038077_0.7069225345652768","host":"s3://npm-registry-packages-npm-production"}},"7.0.0":{"name":"officeparser","version":"7.0.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.0.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"5fc572685e62a0a1c7de39f95d8ff9c577702d13","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.0.0.tgz","fileCount":82,"integrity":"sha512-Ij8QUL5BfT3YjSJXTw5IDoYztFoysmEdLLcg7buOwOacBqLYOBAMLoGsRbL1OBNIiVMo3X1ntyYc0WEPXZz2vQ==","signatures":[{"sig":"MEUCIQCG/d9lL682Rn6JJpk86tEr3yGN/HJKZEAx1jTei0doywIgVq8h4uLhSY4J/ppOsfbMAWz6N9r3k4OyklFAoRIjh0Y=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.0.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2575273},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"43c0a0aa3a6eff0b6d8f49c3f6481e3e369f469c","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.11.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.14.1","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.0.0_1778709269269_0.506462239670781","host":"s3://npm-registry-packages-npm-production"}},"7.0.1":{"name":"officeparser","version":"7.0.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.0.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"5b8ca5989bdc6e0d19e8c8bf6fba533a0e0b9eb7","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.0.1.tgz","fileCount":82,"integrity":"sha512-7vzlaqwbqWqdO6Khvl2WvM5J3VJLm7bamfffOPr0EGVidQ3M1l5i7T6FZjtv1FkSv8Q69nEXgVGkuVvO9NE0XQ==","signatures":[{"sig":"MEUCICNimJqqj24N22mZ9gxWQ25h1dWBMeiJTa7uhJpSZROrAiEA/8ZrkhEHCVQwrd+kMfplyHVlsObZ3l+bGS+Z6V7RMLI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.0.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2585410},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"3b09f6d131c0623261f98e36262ad3609d2948b6","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.11.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.14.1","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.0.1_1778775602727_0.275937483393617","host":"s3://npm-registry-packages-npm-production"}},"7.0.2":{"name":"officeparser","version":"7.0.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.0.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"12f43d8877fceb5e146b48297c20f49e413d2890","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.0.2.tgz","fileCount":82,"integrity":"sha512-VgsixyIE8oBVXBoImBlXaRtKuZ/KEoZbJVygYAL05hxI0bUfD69JPa24rOy2SFovq59BhCpkt1gOLE9tqmxyqA==","signatures":[{"sig":"MEUCIQCZKAOkiQr7pl0TAhdlbCVfEom5XvqAzWwSumTEkYFNhQIgWzSbb4TYdnvvLF21RKm8yGQqMs/wBtOJYU81H/uBEWA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.0.2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2582770},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"0189cfba62ab8f4c361e7f21ad38b9c691454e16","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.11.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.14.1","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.0.2_1778795468400_0.1542322027446148","host":"s3://npm-registry-packages-npm-production"}},"7.0.3":{"name":"officeparser","version":"7.0.3","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.0.3","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"6185bffc9584fd2fb69e9d99745dc61de0572aee","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.0.3.tgz","fileCount":82,"integrity":"sha512-kFYMS0OzIu53/LyRi+l9UIIPpeOVFlz/GVJvsAUrU6IuHBfmc0Y9/C4w/QadQxio7761U/X1frsFRNjAuyBzmg==","signatures":[{"sig":"MEUCICuUhR9l4eaVxbNO8tlUeyBzLrWlCspfdUvQIwXMvqB6AiEAzRPhVbNZTFM91ZvUI35eVjc0fMsGA4mjMp1YgtWyai0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.0.3","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2585146},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"6c83b5f61b5d9c469552492ad3e3dd7d9cb4c853","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.12.1","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.15.0","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.0.3_1778880480105_0.9919304968544318","host":"s3://npm-registry-packages-npm-production"}},"7.1.0":{"name":"officeparser","version":"7.1.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.1.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"7da05c9bfb396bf555aa0292912bf27c73ed43ae","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.1.0.tgz","fileCount":82,"integrity":"sha512-BkN+nQeOWNiwo8ZNesikbtvIKV/ZhB7RlcLmZNdfYrrlaJsceB9zS+YOK+ElaZVKj9vOLQfUvlyByRmoJm6KBg==","signatures":[{"sig":"MEQCIE7HKtXQls9xaG0OkiSPAjlmTbtPCsmiO522ljCn/TPbAiBnywNjJ4E+yxOgFRiVZUAvmZN3Z99aXFms9Q+KNI34Pg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.1.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2627227},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"31b1f5aa1087bd1ad15c63981c2d750805f59a0d","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && mkdir -p docs/test/files && cp test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:visualizer":"node test/testVisualizer.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.12.1","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.15.0","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.1.0_1779746718911_0.9582631793204097","host":"s3://npm-registry-packages-npm-production"}},"7.2.0":{"name":"officeparser","version":"7.2.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.2.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"d8c89e85f13f51bc3baa250a448139949028b61e","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.2.0.tgz","fileCount":82,"integrity":"sha512-X6nSTk5bAyP65mRXX7DnTrHzX0g8YIc0++rWNgsmHWklKgGQB587LEDwgsWOkY7FBxXjPmb42UahDSLg2mD/cA==","signatures":[{"sig":"MEUCIFC0lqLXsCAZ61rPsBe/sij3fpQhNiJPsgSOdCyzvhYkAiEA9HvoKn1coTkVc64GMx3j/87raeMqYPpMkPnODVfYOlk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.2.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":2734929},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"60336a057ebc3e6f4294c4d5b13aa4a88efa4109","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && mkdir -p docs/test/files && cp test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:visualizer":"node test/testVisualizer.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.13.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.16.0","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.2.0_1780608966551_0.695784776259537","host":"s3://npm-registry-packages-npm-production"}},"7.2.1":{"name":"officeparser","version":"7.2.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.2.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"8c450d23059a2a891ef43d9d1e2714a5ea3f9121","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.2.1.tgz","fileCount":82,"integrity":"sha512-l9v4ygeUAZGjNlmXhQNIOaPpxAbLNHzcN32Mwyad/HfGOxLcMGrz8aXMVCGICxtE0s8Mq5MwAEkO9gdliK7hZw==","signatures":[{"sig":"MEUCIENLZtTSD4fTv4i+whtasxi3kNFKpjUeoqJlgUX+SjZlAiEAm3WjhIMnNraoX7NIRK7FXwlJoaGR0jdkRQgN2t8pXmI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.2.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":6272842},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"87d0e60227f2f4d5234737ac6c4828dfa81837c3","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && mkdir -p docs/test/files && cp test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.13.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.16.0","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.2.1_1780826645731_0.23715489479079266","host":"s3://npm-registry-packages-npm-production"}},"7.2.2":{"name":"officeparser","version":"7.2.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.2.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"f29e962a780ba48449a4cec2441cb5da223f8992","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.2.2.tgz","fileCount":82,"integrity":"sha512-W49PyMsOebNsEVEh6jYerNDakK+Se0YdUMwfTjTRQD7qFJqrEuSB7oEagLSnB7YOmZmvpKKz7wJEgeUeJzw5vg==","signatures":[{"sig":"MEUCIQDe4yI4fb8EZlAFurXB9pzMUkcL+1CtNxdcV49kNCc32QIgYR9JkdVSj4WH2Xb7hAiQlgm9070ptlE5I4pBI9/4C2g=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.2.2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":6281437},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"4750b3c7469496f87e11551d89f114b8fec2e3a6","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && mkdir -p docs/test/files && cp test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.13.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.17.0","dependencies":{"fflate":"^0.8.2","file-type":"^22.0.1","pdfjs-dist":"5.6.205","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.27.4","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.1"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.2.2_1782426292646_0.6833500238986074","host":"s3://npm-registry-packages-npm-production"}},"7.2.3":{"name":"officeparser","version":"7.2.3","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.2.3","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"fd427474cd4943abc06e88b710b5362d2fd0fd02","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.2.3.tgz","fileCount":84,"integrity":"sha512-/Ids2DGCw8gt5EDnsk4lB8ABCVEpE067I50jMiuH7GFR2hBGL6PXwWm/GycjuNXzBLAxAOmQhR2XE+S5hR1qwQ==","signatures":[{"sig":"MEUCIDhj0sgefXxc+C36FFJYLDPqVZ9bMWdnl2ObL1yhh9OyAiEArp+tc9+ie9FX7zAr0RWNtxRvUnwh0ditLN2B5hulDwI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.2.3","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":11755737},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"12b5850a16dee8866298d620301d3bb19fa55801","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:generator && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && cp dist/officeparser.browser.slim.iife.js docs/dist/ && cp dist/officeparser.browser.slim.mjs docs/dist/ && mkdir -p docs/test/files && cp test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && cp dist/officeparser.browser.d.ts dist/officeparser.browser.slim.d.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.13.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.17.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.2.3_1782681230541_0.32480820115793163","host":"s3://npm-registry-packages-npm-production"}},"7.3.0":{"name":"officeparser","version":"7.3.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.3.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"02e6c48960ad7ca97b018cfd39f7edca3a3927fd","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.3.0.tgz","fileCount":91,"integrity":"sha512-OfW388kpvh9Gh/2afUjJI+yipPNcJI1oYqQcZI2bw3LORf6pvu3BKpq5c2glDChtwZbK8dEL6S7YjoKIKL0SPg==","signatures":[{"sig":"MEUCIQDhQ39i8RY4vnQ7GSuS+EEqQULrp7iH2OzuYYDVyzE81AIgKb8xf9IlbLo1XrVrk7c/YRRNCGbAqk4Bc5MFBlvW19Q=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.3.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12060969},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"c70571ca40e4e32eaf3cfc9679009511b156aa60","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && cp dist/officeparser.browser.slim.iife.js docs/dist/ && cp dist/officeparser.browser.slim.mjs docs/dist/ && mkdir -p docs/test/files && cp -r test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && cp dist/officeparser.browser.d.ts dist/officeparser.browser.slim.d.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.16.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.18.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.21.0","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.3.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^22.15.0","typescript":"^6.0.2","@types/node":"^25.5.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.59.3","@typescript-eslint/eslint-plugin":"^8.59.3","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.3.0_1783891047212_0.963472152266533","host":"s3://npm-registry-packages-npm-production"}},"7.4.0":{"name":"officeparser","version":"7.4.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.4.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"389f087a8eb7dfa798f9db858cde64f4329987d4","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.4.0.tgz","fileCount":91,"integrity":"sha512-32l/wEJhnpCQ58qK6y79Fk6LxL2NE5/5HEJKEWTv/5J1D/edkMEsf/nkHVVNX+9ctbaeU/QPtQm/Mrr5zJ35Hw==","signatures":[{"sig":"MEYCIQDKVYy5g6RIYrcQVFhwPe8QjPmD78hvavp62gNCSchTiQIhAKdTLHp7JACWPWwmQvfsOT/WmSoYiv1nqBqol1X0TJem","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.4.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12258249},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"a4a5546eb94898054e32f7d0551472f10353abe3","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && cp dist/officeparser.browser.slim.iife.js docs/dist/ && cp dist/officeparser.browser.slim.mjs docs/dist/ && mkdir -p docs/test/files && cp -r test/files/* docs/test/files/","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && cp dist/officeparser.browser.d.ts dist/officeparser.browser.slim.d.ts","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.16.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.18.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.7.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.64.0","@typescript-eslint/eslint-plugin":"^8.64.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.4.0_1784499007390_0.6681492680958312","host":"s3://npm-registry-packages-npm-production"}},"7.5.0":{"name":"officeparser","version":"7.5.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.5.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"48d74d27f1397c42442bf89fc3befe78697c57c4","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.5.0.tgz","fileCount":93,"integrity":"sha512-3OFFz4k3EhMWqz0sLVrerviQOTGl6qP3O9mNLW+N3CCiY4r7BtJWgDDrc8KmRJtsn/bDkMfhnYAoBNMpl1DC4w==","signatures":[{"sig":"MEUCICBtvDeuG0QVWRnEVCWKSeGkKyKM1zhuG/Dbt5yZqGz3AiEAhz0crd6twxJH5CsmDNuE2mvAfhZEa4g7VwF6IXiWsU8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.5.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12328865},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"feb6d8c0d5edcda7c12d898cbe6002848f884134","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && cp dist/officeparser.browser.slim.iife.js docs/dist/ && cp dist/officeparser.browser.slim.mjs docs/dist/ && mkdir -p docs/test/files && cp -r test/files/* docs/test/files/","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && cp dist/officeparser.browser.d.ts dist/officeparser.browser.slim.d.ts","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.16.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.18.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.8.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.65.0","@typescript-eslint/eslint-plugin":"^8.65.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.5.0_1785104320917_0.7769214067352728","host":"s3://npm-registry-packages-npm-production"}},"7.5.1":{"name":"officeparser","version":"7.5.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.5.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"4495a0bf018d872de8e108a0cd3ed29cdd517b05","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.5.1.tgz","fileCount":93,"integrity":"sha512-Gv9146byEWL2e6OpdbrHY3tpgI9+irAG9TrqMvtUpB1bX/o9by7Lm+WjBLPB8pO8mIruIrXSIgCra+jtIGRLgg==","signatures":[{"sig":"MEQCIAFqEdWwkvWDL/ySJawIKGcM0MCF4SLq7GYD4vAH2OabAiB5a7US5fbyFwwB1w0j94nHaxYIdmRcJo3NoGlbIpEhCw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.5.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12382724},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"6e9368ce9dc5fdc70c086c6f1421a07dcc2fc7ba","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"rm -rf dist && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"mkdir -p docs/dist && cp dist/officeparser.browser.iife.js docs/dist/ && cp dist/officeparser.browser.mjs docs/dist/ && cp dist/officeparser.browser.slim.iife.js docs/dist/ && cp dist/officeparser.browser.slim.mjs docs/dist/ && mkdir -p docs/test/files && cp -r test/files/* docs/test/files/","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"rm -rf test/results test/generator/results test/generator/output test/parser/results test/parser/output test/cli/results","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && cp dist/officeparser.browser.d.ts dist/officeparser.browser.slim.d.ts","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.16.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.18.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.8.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.65.0","@typescript-eslint/eslint-plugin":"^8.65.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.5.1_1785445687712_0.7005185316863822","host":"s3://npm-registry-packages-npm-production"}},"7.6.1":{"name":"officeparser","version":"7.6.1","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.6.1","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"507002e6ba3205e9a974e4a70c12ef4d6f814f4a","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.6.1.tgz","fileCount":93,"integrity":"sha512-YWyJK2JngpzQl1VHnN5nxKICh3kMwwnOxLvNC68E/4yPkKuWoH6pURsXQDIePz+oziRg6cxh0gAmBYyxrnZhxQ==","signatures":[{"sig":"MEUCIGomO1VoFzczopZWdB6CS4k7nHMm9ew91KLhYS+GN+uIAiEAhIIqbWIVyyDIqnDo+w1Jz0hBvut2037y4/iKYIYSmZk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.6.1","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12459761},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"85cf5003ea393340fa940230b29ccab2ac63eb22","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\" && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"node -e \"const fs=require('fs');fs.mkdirSync('docs/dist',{recursive:true});for(const f of ['officeparser.browser.iife.js','officeparser.browser.mjs','officeparser.browser.slim.iife.js','officeparser.browser.slim.mjs'])fs.copyFileSync('dist/'+f,'docs/dist/'+f);fs.mkdirSync('docs/test/files',{recursive:true});fs.cpSync('test/files','docs/test/files',{recursive:true})\"","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"node -e \"for(const d of ['test/results','test/generator/results','test/generator/output','test/parser/results','test/parser/output','test/cli/results'])require('fs').rmSync(d,{recursive:true,force:true})\"","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && node -e \"require('fs').copyFileSync('dist/officeparser.browser.d.ts','dist/officeparser.browser.slim.d.ts')\"","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.17.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.19.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.8.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.65.0","@typescript-eslint/eslint-plugin":"^8.65.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.6.1_1786744838751_0.1904843604225248","host":"s3://npm-registry-packages-npm-production"}},"7.6.2":{"name":"officeparser","version":"7.6.2","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.6.2","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"ccb657d4b8174282ef9e430c033ce3149282e9d3","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.6.2.tgz","fileCount":93,"integrity":"sha512-gWPrsipg+umxxwG86eUDS/nncKZ+ymDVJbvTJ7qUFcmBVtd8Q4TNfgaF7tzvvbVW9aMNvoL9TTrvGker4hv1Pw==","signatures":[{"sig":"MEYCIQDo00sLh4sdaGJDnV9fs5dV8CwNnJqKFjMe7V5TwA1JvwIhALfSk3JtDKID0Q9dBaeKdf90Y1U39b0oGYsmJ48/qBlS","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.6.2","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12463810},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"0a3ea3e1aae4d678376948c8ec5fae0c0cd2c895","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\" && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"node -e \"const fs=require('fs');fs.mkdirSync('docs/dist',{recursive:true});for(const f of ['officeparser.browser.iife.js','officeparser.browser.mjs','officeparser.browser.slim.iife.js','officeparser.browser.slim.mjs'])fs.copyFileSync('dist/'+f,'docs/dist/'+f);fs.mkdirSync('docs/test/files',{recursive:true});fs.cpSync('test/files','docs/test/files',{recursive:true})\"","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"node -e \"for(const d of ['test/results','test/generator/results','test/generator/output','test/parser/results','test/parser/output','test/cli/results'])require('fs').rmSync(d,{recursive:true,force:true})\"","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && node -e \"require('fs').copyFileSync('dist/officeparser.browser.d.ts','dist/officeparser.browser.slim.d.ts')\"","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.17.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.19.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.8.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.65.0","@typescript-eslint/eslint-plugin":"^8.65.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.6.2_1786827373287_0.9486085802440207","host":"s3://npm-registry-packages-npm-production"}},"7.7.0":{"name":"officeparser","version":"7.7.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.7.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"647881d61b987d04dc7fbf8dc78ddb8ced18cc13","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.7.0.tgz","fileCount":93,"integrity":"sha512-U93yoEwQINaR31MSgUsIGiNuVN+iWm0V4J3DDI2xIhaOU38G7fq61Ku1tSrn9AQeAipgZmx3pjRDKLSgafepGg==","signatures":[{"sig":"MEUCIQC8BtUlBhoQwR7uKdV6z9/iDGt5Oqjosj0tqc+q6W8oPAIgYHt/L1xD41DZplBVgk5oQIdXxuOQH9UnOTqD+ABOQ1w=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.7.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12510207},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"069a3240f9321820bdd77501963b54ef5a437f7e","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\" && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"node -e \"const fs=require('fs');fs.mkdirSync('docs/dist',{recursive:true});for(const f of ['officeparser.browser.iife.js','officeparser.browser.mjs','officeparser.browser.slim.iife.js','officeparser.browser.slim.mjs'])fs.copyFileSync('dist/'+f,'docs/dist/'+f);fs.mkdirSync('docs/test/files',{recursive:true});fs.cpSync('test/files','docs/test/files',{recursive:true})\"","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"node -e \"for(const d of ['test/results','test/generator/results','test/generator/output','test/parser/results','test/parser/output','test/cli/results'])require('fs').rmSync(d,{recursive:true,force:true})\"","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && node -e \"require('fs').copyFileSync('dist/officeparser.browser.d.ts','dist/officeparser.browser.slim.d.ts')\"","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.17.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.19.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.8.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.65.0","@typescript-eslint/eslint-plugin":"^8.65.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.7.0_1787040098029_0.41489176568809993","host":"s3://npm-registry-packages-npm-production"}},"7.8.0":{"name":"officeparser","version":"7.8.0","keywords":["office","docx","pptx","xlsx","odt","odp","ods","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"author":{"name":"Harsh Ankur"},"license":"MIT","_id":"officeparser@7.8.0","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"homepage":"https://officeparser.harshankur.com","bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"bin":{"officeparser":"dist/cli.js"},"dist":{"shasum":"7f21fc0126cf58447176bd3d71c095150cff7dee","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-7.8.0.tgz","fileCount":93,"integrity":"sha512-z3stbbcwTA4HsGuUz2XJEBbl6WV1X2qCvuiokc2D0593wnu8H7kaD9UY5YAHc8uMjMhH07FxXikzP0BFLSna4A==","signatures":[{"sig":"MEUCIC2Ph0z/FhyEhfzrq/EBl0MEIRJIHJdyY/pKVKXeu9exAiEA53P5Y59Q+lte/GqhTBvXwvehrlPMxb82nAVhxpZXSqk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@7.8.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":12549937},"main":"dist/index.js","types":"dist/index.d.ts","module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"09b27018450ed4df88fe01494343b43556813b71","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\" && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"node -e \"const fs=require('fs');fs.mkdirSync('docs/dist',{recursive:true});for(const f of ['officeparser.browser.iife.js','officeparser.browser.mjs','officeparser.browser.slim.iife.js','officeparser.browser.slim.mjs'])fs.copyFileSync('dist/'+f,'docs/dist/'+f);fs.mkdirSync('docs/test/files',{recursive:true});fs.cpSync('test/files','docs/test/files',{recursive:true})\"","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"node -e \"for(const d of ['test/results','test/generator/results','test/generator/output','test/parser/results','test/parser/output','test/cli/results'])require('fs').rmSync(d,{recursive:true,force:true})\"","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && node -e \"require('fs').copyFileSync('dist/officeparser.browser.d.ts','dist/officeparser.browser.slim.d.ts')\"","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.17.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, PDF, EPUB, and RAG-focused chunks.","directories":{},"sideEffects":false,"_nodeVersion":"24.19.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.0.1","pdfjs-dist":"6.1.200","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.10"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.1","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.8.0","esbuild":"^0.28.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^24.43.1","typescript":"^6.0.3","@types/node":"^26.1.1","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.65.0","@typescript-eslint/eslint-plugin":"^8.65.0","esbuild-plugins-node-modules-polyfill":"^1.8.2"},"peerDependenciesMeta":{"puppeteer":{"optional":true}},"_npmOperationalInternal":{"tmp":"tmp/officeparser_7.8.0_1787090644598_0.7084846362093238","host":"s3://npm-registry-packages-npm-production"}},"8.0.0":{"_id":"officeparser@8.0.0","bin":{"officeparser":"dist/cli.js"},"bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"dist":{"shasum":"5db5aa0cd8c89f4544fe5b79a984fed329b3f350","tarball":"https://registry.npmjs.org/officeparser/-/officeparser-8.0.0.tgz","fileCount":129,"integrity":"sha512-Hwwx0PoIyEIJl7FqzE6nS5MUDKC3sNhYt9SJKuZ+sM1V30bL2CywYE/cwSC9fToqZrmnp8hR7XvhyWKI/x/1Ig==","signatures":[{"sig":"MEYCIQC5Ty5sSKfkdQTOgFMFTqU3hRaZ/4aiCTPxwF0JnYc0fAIhAOspGda9aUku1KoIYoyU0+9k1BMNPhjGFfnac572f3BY","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCID1e5fyBS6PeLF1zvvY4Bwu413NWgxALyH2KJ/rIBPj5AiEAh2RBaLyhiI0JV3PaQx/efLCQCh2JqyFIQB4nRV+Jn6s="}],"attestations":{"url":"https://registry.npmjs.org/-/npm/v1/attestations/officeparser@8.0.0","provenance":{"predicateType":"https://slsa.dev/provenance/v1"}},"unpackedSize":27764277},"main":"dist/index.js","name":"officeparser","types":"dist/index.d.ts","author":{"name":"Harsh Ankur"},"module":"dist/index.mjs","browser":"./dist/officeparser.browser.mjs","engines":{"node":">=22.13.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.mjs","browser":"./dist/officeparser.browser.mjs","require":"./dist/index.js"},"./slim":{"types":"./dist/officeparser.browser.slim.d.ts","import":"./dist/officeparser.browser.slim.mjs","browser":"./dist/officeparser.browser.slim.mjs","default":"./dist/officeparser.browser.slim.mjs"},"./browser-native-pdf":{"types":"./dist/officeparser.browser.d.ts","import":"./dist/officeparser.browser.native-pdf.mjs","browser":"./dist/officeparser.browser.native-pdf.mjs","default":"./dist/officeparser.browser.native-pdf.mjs"}},"funding":"https://github.com/sponsors/harshankur","gitHead":"222487e391c25f32fd94d15d3f305c15798082c5","license":"MIT","scripts":{"lint":"eslint src","sbom":"npx --yes @cyclonedx/cyclonedx-npm --output-format json --output-file dist/sbom.cdx.json --omit dev","test":"npm run lint && npm run test:clean && npm run build && npm run test:license && npm run test:artifacts && npm run test:parser && npm run test:exhaustive && npm run test:generator && npm run test:security && npm run test:cli","build":"npm run sync:versions && npm run build:node && npm run build:esm-wrapper && npm run build:browser:types && npm run build:browser","clean":"node -e \"require('fs').rmSync('dist',{recursive:true,force:true})\" && npm run test:clean","prepare":"husky","test:cli":"npx tsx test/cli/testCli.ts","sync:docs":"node -e \"const fs=require('fs');fs.mkdirSync('docs/dist',{recursive:true});for(const f of ['officeparser.browser.iife.js','officeparser.browser.mjs','officeparser.browser.slim.iife.js','officeparser.browser.slim.mjs'])fs.copyFileSync('dist/'+f,'docs/dist/'+f);fs.mkdirSync('docs/test/files',{recursive:true});fs.cpSync('test/files','docs/test/files',{recursive:true})\"","test:fast":"npm run lint && npm run test:parser:fast && npm run test:exhaustive && npm run test:generator:fast && npm run test:security && npm run test:cli:fast","build:node":"tsc","test:clean":"node -e \"for(const d of ['test/results','test/generator/results','test/generator/output','test/parser/results','test/parser/output','test/cli/results'])require('fs').rmSync(d,{recursive:true,force:true})\"","test:parser":"npx tsx test/parser/testOfficeParser.ts","test:license":"npm run sbom && node scripts/validate-licenses.js","build:browser":"node build_browser.js && npm run sync:docs","sync:versions":"node scripts/sync-pdfjs-versions.js","test:baseline":"npm run test:parser:baseline && npm run test:generator:baseline","test:cli:fast":"npx tsx test/cli/testCli.ts fast","test:security":"npx tsx test/security/testSanitization.ts","prepublishOnly":"npm run clean && npm run build","test:artifacts":"npx tsx test/testShippingArtifacts.ts","test:generator":"npx tsx test/generator/testOfficeGenerator.ts","test:exhaustive":"npx tsx test/testExhaustive.ts","test:visualizer":"node test/testVisualizer.js","test:integration":"node test/testIntegration.js","test:parser:fast":"npx tsx test/parser/testOfficeParser.ts fast","build:esm-wrapper":"node scripts/generate-esm-wrapper.js","build:browser:types":"dts-bundle-generator --no-check -o dist/officeparser.browser.d.ts src/index.ts && node -e \"require('fs').copyFileSync('dist/officeparser.browser.d.ts','dist/officeparser.browser.slim.d.ts')\"","test:generator:fast":"npx tsx test/generator/testOfficeGenerator.ts fast","test:parser:baseline":"npx tsx test/parser/testOfficeParser.ts baseline","test:generator:baseline":"npx tsx test/generator/testOfficeGenerator.ts baseline"},"version":"8.0.0","_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:46eca351-4ec7-4466-80f4-58b4ab1e3327"}},"homepage":"https://officeparser.harshankur.com","keywords":["office","docx","pptx","xlsx","odt","odp","ods","odg","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"_npmVersion":"11.19.0","description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .odg, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in DOCX, ODT, Markdown, HTML, CSV, RTF, PDF, EPUB, and RA","directories":{},"maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"sideEffects":false,"_nodeVersion":"24.20.0","dependencies":{"fflate":"^0.8.3","file-type":"^22.1.0","pdfjs-dist":"6.2.108","tesseract.js":"^7.0.0","@xmldom/xmldom":"^0.9.12"},"publishConfig":{"access":"public","provenance":true},"_hasShrinkwrap":false,"devDependencies":{"tsx":"^4.23.12","husky":"^9.1.7","buffer":"^6.0.3","eslint":"^10.9.1","esbuild":"^0.28.2","pdf-lib":"^1.17.1","process":"^0.11.10","postject":"^1.0.0-alpha.6","puppeteer":"^25.9.0","typescript":"^6.0.3","@types/node":"^26.4.0","dts-bundle-generator":"^9.5.1","@typescript-eslint/parser":"^8.70.0","@typescript-eslint/eslint-plugin":"^8.70.0","esbuild-plugins-node-modules-polyfill":"^1.8.3"},"peerDependencies":{"pdf-lib":"^1.17.1","puppeteer":">=22"},"peerDependenciesMeta":{"pdf-lib":{"optional":true},"puppeteer":{"optional":true}},"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/officeparser_8.0.0_1789596760924_0.6347702910009603"}}},"time":{"created":"2019-04-15T10:37:25.848Z","modified":"2026-09-16T22:12:41.519Z","1.0.0":"2019-04-15T10:37:26.030Z","1.0.1":"2019-04-15T10:47:12.135Z","1.1.0":"2019-04-18T15:12:52.976Z","1.1.1":"2019-04-18T15:18:46.436Z","1.1.2":"2019-04-18T15:28:21.018Z","1.2.0":"2019-04-19T13:36:09.121Z","1.2.1":"2019-04-22T06:42:35.882Z","1.3.0":"2019-04-22T09:23:45.067Z","1.4.0":"2019-04-23T01:44:54.097Z","1.4.1":"2019-04-23T01:49:56.949Z","2.0.0":"2019-04-23T03:03:53.634Z","2.0.1":"2019-04-25T14:52:24.265Z","2.0.2":"2019-04-28T14:07:13.512Z","2.0.3":"2019-04-30T13:06:35.147Z","2.1.0":"2019-06-17T14:00:49.391Z","2.1.1":"2019-06-17T14:09:53.010Z","2.2.1":"2020-06-01T06:05:13.341Z","2.2.2":"2020-06-01T06:07:40.507Z","2.3.0":"2021-11-21T13:34:48.926Z","3.0.0":"2022-12-10T00:20:17.716Z","3.1.0":"2022-12-24T23:06:19.297Z","3.1.1":"2022-12-28T07:26:02.162Z","3.1.2":"2022-12-28T07:38:29.685Z","3.1.3":"2022-12-28T07:44:15.425Z","3.1.4":"2022-12-28T07:45:22.252Z","3.2.0":"2023-04-07T13:26:02.827Z","3.2.1":"2023-04-15T21:27:38.561Z","3.2.2":"2023-04-15T21:35:18.947Z","3.3.0":"2023-04-26T20:45:11.739Z","4.0.0":"2023-10-25T09:58:09.151Z","4.0.1":"2023-10-25T10:35:11.286Z","4.0.2":"2023-10-25T12:09:48.081Z","4.0.3":"2023-10-25T12:46:08.592Z","4.0.4":"2023-10-25T12:57:30.917Z","4.0.5":"2023-11-25T20:23:21.922Z","4.0.6":"2024-01-02T21:00:29.665Z","4.0.7":"2024-02-07T21:46:21.701Z","4.0.8":"2024-02-11T22:12:38.496Z","4.1.0":"2024-05-06T18:29:39.230Z","4.1.1":"2024-05-06T19:09:00.445Z","4.1.2":"2024-10-13T20:23:54.053Z","4.2.0":"2024-10-14T22:50:16.096Z","5.0.0":"2024-10-21T20:56:12.469Z","5.1.1":"2024-11-11T23:41:54.263Z","5.2.0":"2025-07-05T20:04:06.286Z","5.2.1":"2025-09-29T21:26:26.611Z","5.2.2":"2025-11-12T12:04:43.895Z","6.0.1":"2026-01-02T15:03:21.171Z","6.0.2":"2026-01-08T12:17:24.097Z","6.0.3":"2026-01-10T14:46:49.756Z","6.0.4":"2026-01-10T15:33:55.448Z","6.0.6":"2026-03-23T23:40:13.281Z","6.0.7":"2026-03-24T11:32:36.586Z","6.1.0":"2026-04-14T14:09:36.960Z","6.1.1":"2026-04-28T22:07:18.281Z","7.0.0":"2026-05-13T21:54:29.439Z","7.0.1":"2026-05-14T16:20:02.897Z","7.0.2":"2026-05-14T21:51:08.603Z","7.0.3":"2026-05-15T21:28:00.267Z","7.1.0":"2026-05-25T22:05:19.064Z","7.2.0":"2026-06-04T21:36:06.720Z","7.2.1":"2026-06-07T10:04:05.903Z","7.2.2":"2026-06-25T22:24:52.858Z","7.2.3":"2026-06-28T21:13:50.780Z","7.3.0":"2026-07-12T21:17:27.442Z","7.4.0":"2026-07-19T22:10:07.647Z","7.5.0":"2026-07-26T22:18:41.148Z","7.5.1":"2026-07-30T21:08:07.989Z","7.6.1":"2026-08-14T22:00:39.002Z","7.6.2":"2026-08-15T20:56:13.553Z","7.7.0":"2026-08-18T08:01:38.287Z","7.8.0":"2026-08-18T22:04:04.877Z","8.0.0":"2026-09-16T22:12:41.182Z"},"bugs":{"url":"https://github.com/harshankur/officeParser/issues"},"author":{"name":"Harsh Ankur"},"license":"MIT","homepage":"https://officeparser.harshankur.com","keywords":["office","docx","pptx","xlsx","odt","odp","ods","odg","pdf","rtf","csv","parser","text extraction","document parser","word","excel","powerpoint","spreadsheet","presentation","slides","ast","ocr","typescript","browser","metadata","formatting","attachments","tesseract","pdf.js","structured-data","openoffice","libreoffice","generator","rag","chunking","markdown","html","epub","ebook"],"repository":{"url":"git+https://github.com/harshankur/officeParser.git","type":"git"},"description":"A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .odg, .pdf, .rtf, .csv, .md, .html, .epub) and generating high-fidelity outputs in DOCX, ODT, Markdown, HTML, CSV, RTF, PDF, EPUB, and RA","maintainers":[{"name":"harshankur","email":"harshankur@outlook.com"}],"readme":"# officeParser: Universal Office Document Parser & Generator\n\nA robust, strictly-typed **Node.js and Browser** library for parsing office files into a rich **Abstract Syntax Tree (AST)** and generating high-fidelity output in multiple formats.\n\n**Parses:** [`docx`](https://en.wikipedia.org/wiki/Office_Open_XML) · [`pptx`](https://en.wikipedia.org/wiki/Office_Open_XML) · [`xlsx`](https://en.wikipedia.org/wiki/Office_Open_XML) · [`odt`](https://en.wikipedia.org/wiki/OpenDocument) · [`odp`](https://en.wikipedia.org/wiki/OpenDocument) · [`ods`](https://en.wikipedia.org/wiki/OpenDocument) · [`odg`](https://en.wikipedia.org/wiki/OpenDocument) · [`pdf`](https://en.wikipedia.org/wiki/PDF) · [`rtf`](https://en.wikipedia.org/wiki/Rich_Text_Format) · [`csv`](https://en.wikipedia.org/wiki/Comma-separated_values) · [`md`](https://en.wikipedia.org/wiki/Markdown) · [`html`](https://en.wikipedia.org/wiki/HTML) · [`epub`](https://en.wikipedia.org/wiki/EPUB)\n\n**Generates:** `DOCX` · `ODT` · `Markdown` · `HTML` · `CSV` · `RTF` · `PDF` · `EPUB` · `Plain Text` · `RAG Chunks`\n\n[![npm version](https://badge.fury.io/js/officeparser.svg)](https://badge.fury.io/js/officeparser)\n[![Total Downloads](https://img.shields.io/npm/dt/officeparser.svg)](https://www.npmjs.com/package/officeparser)\n[![Weekly Downloads](https://img.shields.io/npm/dw/officeparser.svg)](https://www.npmjs.com/package/officeparser)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\n---\n\n### 🌟 [Live Interactive AST Visualizer & Documentation](https://harshankur.github.io/officeParser/) 🌟\n*Upload any office file in your browser: inspect the AST, tweak config, and preview generated output in real-time.*\n\n- **AST Visualizer**: Inspect the hierarchical node tree, metadata, and raw content\n- **Config Configurator**: Tweak options (`ignoreNotes`, `ocr`, `newlineDelimiter`) and see results instantly\n- **Debugging**: Identify exactly how nodes are interpreted\n- **Format Specs**: Read detailed specs for the AST structure and all config options\n\n---\n\n### 📝 [Changelog](CHANGELOG.md)\n\n---\n\n## What's New in v8\n\n- **Rebuilt PDF text extraction.** PDF is no longer treated as a page of flat lines. Tagged PDFs now yield real `heading` (with correct levels), `table`/`row`/`cell`, `list` and footnote/endnote `note` nodes, and one `paragraph` per paragraph. Untagged PDFs recover the same structure geometrically. Multi-column and float-beside-text pages are read in the correct order (recursive XY-cut), broken and glued words are fixed from inter-fragment spacing, super/subscripts and hyphenated line-breaks are rejoined, rotated text is recovered, and internal links resolve to the target section. `.to('text')` is **layout-faithful by default**, rendering each page as a spatial grid so columns and tables line up like the source. Per-run color/highlight extraction (on by default; set `pdfParserConfig.extractTextColor: false` to skip it) and merged-cell (`colSpan`/`rowSpan`) recovery round it out, and every node carries page geometry (`bounds`).\n- **Password-protected documents.** Encrypted PDF, OOXML (`docx`/`xlsx`/`pptx`) and ODF (`odt`/`ods`/`odp`/`odg`) open through one unified `password` / `onPassword` option, across parsing, conversion and templating.\n- **Native DOCX & ODT generation**, plus a **native PDF engine** (`pdfConfig.engine: 'native'`, built on `pdf-lib`) that produces real PDF bytes with no headless browser, in Node and the browser alike.\n- **Templates / mail-merge** via `OfficeTemplate.render` (fill a DOCX template's `{{placeholders}}`, single or batch), and **ODG parsing** (LibreOffice Draw).\n\nSee the [full changelog](CHANGELOG.md) for the complete list, including breaking changes.\n\n---\n\n## Table of Contents\n- [What's New in v8](#whats-new-in-v8)\n- [Install](#install-via-npm)\n- [Command Line Usage](#command-line-usage)\n- [Quick Decision Guide](#quick-decision-guide)\n- [Library Usage: Parsing](#library-usage-parsing)\n  - [Async/Await](#asyncawait)\n  - [Callback (Backward Compat)](#callback-backward-compat)\n  - [File Buffers, ArrayBuffers & Blobs](#file-buffers-arraybuffers--blobs)\n  - [`ast.to()`: Generate from AST](#astto-generate-from-ast)\n  - [`.to('text')`: Plain Text Extraction](#totext-plain-text-extraction)\n- [OfficeGenerator](#officegenerator)\n- [OfficeConverter: One-Step API](#officeconverter-one-step-api)\n- [OfficeTemplate: Mail-Merge / Document Generation](#officetemplate-mail-merge--document-generation)\n- [Native RAG Chunking](#native-rag-chunking)\n- [The AST Structure](#the-ast-structure)\n- [Deep Dive: Document Components](#deep-dive-document-components)\n- [Markdown Dialect Support](#markdown-dialect-support)\n- [EPUB Support](#epub-support)\n- [Performance Highlights](#performance-highlights)\n- [Advanced AST Usage](#advanced-ast-usage)\n- [Configuration Reference](#configuration-reference)\n  - [OfficeParserConfig](#officeparserconfig)\n  - [GeneratorConfig (Common)](#generatorconfig-common)\n  - [onNode Callback](#onnode-callback-advanced-node-manipulation)\n  - [styleMap: Semantic Style Mapping](#stylemap-semantic-style-mapping)\n  - [HtmlGeneratorConfig](#htmlgeneratorconfig)\n  - [MdGeneratorConfig](#mdgeneratorconfig)\n  - [PdfGeneratorConfig](#pdfgeneratorconfig)\n  - [DocxGeneratorConfig](#docxgeneratorconfig)\n  - [OdtGeneratorConfig](#odtgeneratorconfig)\n  - [CsvGeneratorConfig](#csvgeneratorconfig)\n  - [TextGeneratorConfig](#textgeneratorconfig)\n  - [metadataOverrides](#metadataoverrides)\n  - [OfficeConverterConfig](#officeconverterconfig)\n  - [ChunkingConfig](#chunkingconfig)\n- [OCR Scheduler & Resource Management](#ocr-scheduler--resource-management)\n- [Browser Usage](#browser-usage)\n- [Troubleshooting & Common Issues](#troubleshooting--common-issues)\n- [Known Limitations](#known-limitations)\n- [Security & Trust Boundary](#security--trust-boundary)\n- [Contributing](#contributing)\n\n---\n\n## Install via npm\n\n```bash\nnpm i officeparser\n```\n\n> [!NOTE]\n> Requires Node.js >= 22.13.\n\n---\n\n## Command Line Usage\n\n```bash\n# Full AST as JSON (default)\nnpx officeparser /path/to/file.docx\n\n# Plain text output\nnpx officeparser /path/to/file.docx --to=text\n\n# Convert DOCX to Markdown and save\nnpx officeparser report.docx --to=md --output=report.md\n\n# Convert PPTX to HTML with OCR (OCR runs over extracted images, so --extractAttachments is required)\nnpx officeparser presentation.pptx --to=html --output=preview.html --ocr --extractAttachments\n\n# Convert XLSX to CSV with a custom delimiter\nnpx officeparser data.xlsx --to=csv --csvDelimiter=\";\"\n\n# Generate RAG chunks\nnpx officeparser document.pdf --to=chunks\n\n# Convert DOCX to EPUB (--extractAttachments is required to embed images)\nnpx officeparser book.docx --extractAttachments --to=epub --output=book.epub\n\n# Convert Markdown (or any source) to a Word document\nnpx officeparser notes.md --extractAttachments --to=docx --output=notes.docx\n\n# Convert a Word document (or any source) to OpenDocument Text\nnpx officeparser report.docx --extractAttachments --to=odt --output=report.odt\n\n# Overriding file extension mapping\nnpx officeparser my_document --fileType=docx --to=json\n```\n\n### CLI Syntax\n- **Values:** Flags can be passed as `--flag=value` or `--flag value`.\n- **Booleans:** Bare flags imply `true` (e.g. `--ocr` is equivalent to `--ocr=true`). Negation flags start with `no-` (e.g. `--no-ocr` is equivalent to `--ocr=false`).\n- **Nested Objects:** You can pass nested properties directly using JSON dot-notation (e.g. `--ocrConfig.language=fra` or `--htmlConfig.containerWidth=900px`).\n- **Images:** the CLI parses directly, so add `--extractAttachments` for images to reach *any* output (HTML/EPUB embed them, DOCX/ODT/Markdown/native-PDF include them). Without it, an image node has no bytes and HTML/Markdown emit a name-only `<img src=\"image1.png\">` reference. (The `OfficeConverter`/`convert()` API auto-enables this; the CLI does not.)\n\n### CLI Options\n\n| Flag | Values | Default | Description |\n|------|--------|---------|-------------|\n| `--to` | `json\\|text\\|md\\|html\\|csv\\|rtf\\|pdf\\|docx\\|odt\\|epub\\|chunks` | `json` | Output format |\n| `--output` | path | (none) | Write output to a file |\n| `--fileType` | `docx\\|xlsx\\|pptx\\|odt\\|odp\\|ods\\|odg\\|pdf\\|rtf\\|csv\\|md\\|html\\|epub` | (none) | Explicitly override input file type detection |\n| `--ocr` | boolean | `false` | Enable OCR for images (also requires `--extractAttachments`; OCR runs over extracted images) |\n| `--ocrConfig.language` | string | `eng` | Tesseract language(s), e.g. `deu` or `eng+fra` |\n| `--ocrConfig.preserveLayout` | boolean | `true` | Keep the line layout of recognized text |\n| `--password` | string | (none) | Password for an encrypted document (PDF, OOXML, or ODF) |\n| `--extractAttachments` | boolean | `false` | Extract images/charts as Base64 |\n| `--ignoreNotes` | boolean | `false` | Ignore footnotes/endnotes/speaker notes |\n| `--ignoreComments` | boolean | `false` | Ignore inline comments |\n| `--ignoreHeadersAndFooters` | boolean | `false` | Ignore headers and footers |\n| `--ignoreSlideMasters` | boolean | `false` | Ignore slide masters |\n| `--ignoreInternalLinks` | boolean | `false` | Ignore internal links |\n| `--newlineDelimiter` | string | `\\n` | Delimiter between lines/blocks in plaintext outputs |\n| `--csvDelimiter` | string | `,` | Custom delimiter for CSV files |\n| `--includeRawContent` | boolean | `false` | Include raw XML/RTF in nodes |\n| `--serializeRawContent` | boolean | `true` | Include stringified XML in metadata |\n| `--preserveXmlWhitespace` | boolean | `false` | Keep raw formatting space |\n| `--includeBreakNodes` | boolean | `false` | Include break nodes (DOCX and ODF) |\n| `--ignorePageGeometry` | boolean | `false` | Omit per-node bounding boxes and page dimensions |\n| `--pdfParserConfig.useTags` | boolean | `true` | Use the PDF tag tree; `false` forces geometry-only structure |\n| `--pdfParserConfig.detectColumns` | boolean | `true` | Multi-column reading-order detection |\n| `--pdfParserConfig.pageRange` | string | all | Parse only the given pages, e.g. `1-3,7` |\n| `--pdfParserConfig.headingDetection` | `auto\\|font-size\\|off` | `auto` | How headings are inferred on the geometry path |\n| `--pdfParserConfig.mergeHyphenatedWords` | boolean | `true` | Rejoin words hyphenated across line breaks |\n| `--pdfParserConfig.normalizeText` | boolean | `true` | Unicode/ligature normalization of extracted text |\n| `--pdfParserConfig.extractTextColor` | boolean | `true` | Record each run's fill colour in `formatting.color` (set `false` to skip for speed) |\n| `--verbose` | boolean | `false` | Show full error stack traces and warning logs |\n| `--includeFormatting` | boolean | `true` | Include formatting style map matching |\n| `--renderMetadata` | boolean | `false` | Render metadata as visible content in the generated output |\n| `--includeImages` | `image-only\\|image+ocr-text\\|ocr-text-only\\|none` | `image-only` | How image nodes render. Works as `--includeImages=<mode>` or `--includeImages <mode>`; a bare `--includeImages` means `image-only` |\n| `--maxInlineImageBytes` | number | `1500000` | Largest image HTML/Markdown inlines as a `data:` URI (`0` never inlines) |\n| `--htmlConfig.containerWidth` | string \\| number | `auto` | HTML output container width (e.g. `900px`, `100%`) |\n| `--textConfig.pageSeparator` | string | `\\n` | Separator written between pages in text output |\n| `--pdfConfig.engine` | `html\\|native` | `html` | PDF engine: Puppeteer (`html`) or pdf-lib (`native`, no browser) |\n| ~~`--format`~~ | `json\\|text\\|md\\|html\\|csv\\|rtf\\|pdf\\|docx\\|odt\\|epub\\|chunks` | `json` | **Deprecated.** Use `--to` |\n| ~~`--toText`~~ | | | **Removed in v8.** Use `--to=text`. |\n| ~~`--ocrLanguage`~~ | | | **Removed in v8.** Use `--ocrConfig.language`. |\n| ~~`--putNotesAtLast`~~ | | | **Removed in v8.** Notes are attached structurally via `node.notes`. |\n| ~~`--outputErrorToConsole`~~ | | | **Removed in v8.** Use `--verbose`. |\n\nEvery removed flag above exits with status 1 and prints its replacement, rather than being accepted\nand ignored. An unrecognized or renamed **config** key (say `--ocrConfig.autoTerminateTimeout`) is not fatal, but the\nCLI always prints the warning naming its replacement, with or without `--verbose`.\n\n---\n\n## Quick Decision Guide\n\n| Goal | API to use |\n|------|-----------|\n| Extract text / AST from a file | `OfficeParser.parseOffice(file)` |\n| Convert directly to another format | `OfficeConverter.convert(file, 'md')` |\n| Parse first, then generate | `parseOffice()` → `OfficeGenerator.generate(ast, 'html')` |\n| Convert on the AST itself (shorthand) | `ast.to('md')` |\n| RAG pipeline chunking | `OfficeConverter.convert(file, 'chunks', {...})` |\n\n---\n\n## Library Usage: Parsing\n\n### Async/Await\n\n```js\nconst officeParser = require('officeparser');\n\nconst ast = await officeParser.parseOffice('/path/to/file.docx');\n\nconsole.log(ast.type);       // 'docx'\nconsole.log(ast.metadata);   // { author, title, created, ... }\nconsole.log(ast.content);    // Array of hierarchical nodes\nconsole.log(ast.attachments);// Images/charts (if extractAttachments: true)\nconsole.log(ast.warnings);   // Non-fatal issues from parsing phase\n```\n\n**TypeScript (named import):**\n```ts\nimport { OfficeParser } from 'officeparser';\n\nconst ast = await OfficeParser.parseOffice('report.docx', {\n    extractAttachments: true,\n    ocr: true,\n});\n```\n\n### Callback (Backward Compat)\n\n```js\nofficeParser.parseOffice('/path/to/file.docx', async function(ast, err) {\n    if (err) { console.error(err); return; }\n    console.log((await ast.to('text')).value);\n});\n```\n\n### File Buffers, ArrayBuffers & Blobs\n\nPass a `Buffer`, `ArrayBuffer`, `Uint8Array`, or a web `Blob`/`File` instead of a file path:\n\n```js\nconst fs = require('fs');\nconst buffer = fs.readFileSync('/path/to/file.pdf');\nconst ast = await officeParser.parseOffice(buffer);\n```\n\nIn the browser you can hand a `File`/`Blob` straight from an `<input type=\"file\">` — no need to\nread it into a buffer first. A `File`'s name drives type detection, so no `fileType` hint is\nneeded when the name has a recognizable extension:\n\n```js\n// input.files[0] is a File (e.g. \"report.docx\")\nconst ast = await officeParser.parseOffice(input.files[0]);\n```\n\n> [!IMPORTANT]\n> **Text-based formats from buffers need a `fileType` hint.**\n> Formats like `md`, `html`, and `csv` have no magic bytes, so the parser cannot\n> auto-detect them from a buffer. You **must** provide `fileType` in that case:\n> ```js\n> const ast = await officeParser.parseOffice(markdownBuffer, { fileType: 'md' });\n> ```\n\n> [!NOTE]\n> **ZIP-backed formats are identified from inside the archive.** DOCX, XLSX, PPTX, ODT, ODS, ODP\n> and EPUB are all ZIP files, and telling them apart from the first bytes alone is unreliable for\n> archives written by streaming producers or holding very many parts. When the byte signature is\n> inconclusive, the archive is opened and the format is read from its own declaration\n> (`[Content_Types].xml`, or the `mimetype` entry), so these parse from a buffer without a hint.\n> Supplying `fileType` remains the fastest and most certain route: it decides which parser runs,\n> and for these formats no archive inspection is done at all.\n\n### Cancellation with AbortSignal\n\nYou can pass a standard `AbortSignal` (e.g. from an `AbortController`) to cancel an active parse operation. This is especially useful for setting request-level timeouts or canceling long-running parses (like large PDFs with OCR).\n\n```js\nconst controller = new AbortController();\n\n// Cancel parsing if it takes longer than 5 seconds\nsetTimeout(() => controller.abort(), 5000);\n\ntry {\n    const ast = await officeParser.parseOffice('large_scanned_file.pdf', {\n        abortSignal: controller.signal,\n        ocr: true,\n        extractAttachments: true // page-image OCR needs this; ocr alone does nothing\n    });\n} catch (err) {\n    if (err.name === 'AbortError') {\n        console.log('Parsing was cancelled.');\n    } else {\n        console.error('Parsing failed:', err);\n    }\n}\n```\n\n> [!IMPORTANT]\n> **AbortError Propagation**\n> When parsing is cancelled via `AbortSignal`, the parser rejects with a standard `AbortError` (a `DOMException` or an Error with `name: 'AbortError'`).\n> This error is *not* wrapped in standard OfficeParser error types so that you can reliably detect cancellation using `error.name === 'AbortError'`.\n\n> [!NOTE]\n> **Worker Cleanup on Abort**\n> If an OCR job is actively running in the background when the signal is aborted, `officeParser` automatically terminates the Tesseract worker process immediately and removes it from the pool to prevent thread/memory leaks.\n\n### Custom OCR Timeouts\n\nTo prevent the parser from hanging indefinitely due to slow network connections (when downloading Tesseract language datasets) or complex image processing, you can configure granular timeouts under `ocrConfig.timeout`.\n\n```js\nconst ast = await officeParser.parseOffice('scanned_document.pdf', {\n    ocr: true,\n    extractAttachments: true, // required: OCR of a PDF's page images runs through the attachment path\n    ocrConfig: {\n        timeout: {\n            workerLoad: 30000,    // 30s max to load worker & download language training files\n            recognition: 15000,   // 15s max per image text recognition\n            autoTerminate: 10000  // 10s of inactivity before terminating idle workers\n        }\n    }\n});\n```\n\n> [!TIP]\n> **Non-Fatal Timeout Recovery**\n> If `workerLoad` or `recognition` timeouts are exceeded, the parser will log a warning in `ast.warnings` and **continue parsing the rest of the document**. The overall promise resolves successfully with the text extracted from the document layers (rather than failing the entire parse).\n\n### OCR Layout Reconstruction\n\nBy default (`ocrConfig.preserveLayout: true`) the recognized text keeps its two-dimensional page layout, rebuilt from Tesseract's per-word bounding boxes: a scanned table, form or multi-column page keeps its columns (right-hand text stays on the right, labels and values line up) instead of collapsing to a flat reading-order string. It is the OCR analogue of `textConfig.preserveLayout` for born-digital PDFs. Set it `false` for the plain, linearized text.\n\n```js\nconst ast = await officeParser.parseOffice('scanned_invoice.pdf', {\n    ocr: true,\n    extractAttachments: true, // required: OCR of a PDF's page images runs through the attachment path\n    ocrConfig: { preserveLayout: true } // default; false = flat reading-order text\n});\n```\n\n### `ast.to()`: Generate from AST\n\nThe preferred way to convert a parsed AST to another format. Returns a `ConversionResult`.\n\n```ts\n// ConversionResult shape:\n// { value: string | Uint8Array | OfficeChunk[], messages: OfficeIssue[] }\n\nconst { value: markdown, messages } = await ast.to('md');\nconst { value: html }               = await ast.to('html', { includeFormatting: false });\nconst { value: chunks }             = await ast.to('chunks', { chunksConfig: { strategy: 'fixed-size', chunkSize: 800 } });\nconst { value: pdfBytes }           = await ast.to('pdf'); // Uint8Array\n```\n\n### `.to('text')`: Plain Text Extraction\n\nPlain text comes from `.to('text')`, which is asynchronous and configurable. Its defaults render\ntables as aligned grids, lists with markers and indentation, and include notes and image\nplaceholders:\n\n```js\n// Default: aligned tables, list markers, notes, image placeholders, layout-faithful PDF pages\nconst { value } = await ast.to('text');\n\n// Flat stream of text, no grid alignment or markers\nconst { value } = await ast.to('text', {\n    includeImages: false,\n    textConfig: { preserveLayout: false, renderNotes: false },\n});\n```\n\n| Feature | default | flat (`preserveLayout: false`) | governed by |\n|---|---|---|---|\n| Tables | aligned grid | one cell per line, tab-separated | `textConfig.preserveLayout` (default `true`) |\n| Lists | markers + indentation | plain text | `textConfig.preserveLayout` (default `true`) |\n| PDF pages | spatial monospace grid (columns/tables aligned like the page) | flowing text | `textConfig.preserveLayout` + geometry |\n| Footnotes/endnotes | emitted | emitted | `textConfig.renderNotes` (default `true`) |\n| Image placeholders | emitted | emitted | `includeImages` (default `true`) |\n\nFor PDFs with page geometry (the default, unless `ignorePageGeometry` is set), `preserveLayout` renders\neach page as a spatial monospace grid so multi-column text and tables line up much like the original\npage, similar to `pdftotext -layout`. Use `textConfig.pageSeparator` (default `'\\n'`, or `'\\f'` for a\nform feed) to control what goes between pages.\n\nSpreadsheets (CSV/ODS/XLSX) are unaffected by `preserveLayout`: it governs `table`/`list` nodes,\nwhile spreadsheet content is `sheet`/`row`/`cell`. There the default aligned grid is the most\nfaithful rendering.\n\n> [!NOTE]\n> The synchronous `ast.toText()` method was **removed in v8**. Use `(await ast.to('text')).value`,\n> which produces the same content at its defaults and adds the configuration above.\n\n---\n\n## OfficeGenerator\n\nUse `OfficeGenerator.generate(ast, format, config?)` when you need to produce output from an already-parsed AST:\n\n```ts\nimport { OfficeParser, OfficeGenerator } from 'officeparser';\n\nconst ast = await OfficeParser.parseOffice('report.docx');\n\n// Convert to Markdown\nconst { value: md } = await OfficeGenerator.generate(ast, 'md');\n\n// Convert to HTML with style mapping\nconst { value: html } = await OfficeGenerator.generate(ast, 'html', {\n    includeFormatting: true,\n    styleMap: [\n        {\n            selector: { nodeType: 'paragraph', attributes: { style: 'Heading 1' } },\n            output: { tag: 'h1', classes: ['main-title'] }\n        }\n    ]\n});\n\n// Convert to CSV (spreadsheets)\nconst { value: csv } = await OfficeGenerator.generate(ast, 'csv');\n```\n\n**Supported destinations:** `'text'` · `'md'` · `'html'` · `'csv'` · `'rtf'` · `'pdf'` · `'docx'` · `'odt'` · `'epub'` · `'chunks'`\n\n> [!NOTE]\n> **PDF generation** uses a headless browser by default (`pdfConfig.engine: 'html'`), which needs the\n> optional `puppeteer` peer dependency:\n> ```bash\n> npm install puppeteer\n> ```\n> Or choose `pdfConfig.engine: 'native'` to lay the document out directly with `pdf-lib`\n> (`npm install pdf-lib`): no browser, and the only engine that produces a real PDF in the browser\n> (import from `officeparser/browser-native-pdf` for the client-side path).\n> See [PdfGeneratorConfig](#pdfgeneratorconfig).\n>\n> **EPUB generation with images** requires `extractAttachments: true` on the parse step that\n> produced the AST — see [EPUB Support](#epub-support).\n\n---\n\n## OfficeConverter: One-Step API\n\n`OfficeConverter.convert()` combines parsing and generation in a single call. It automatically syncs parser options from the generator config: unless you set `parseConfig.extractAttachments` explicitly, it is enabled when the output will render images or charts, or when you enable `parseConfig.ocr`. An explicit `parseConfig.extractAttachments` (including `false`) always wins, and `parseConfig.ocr` is honored (so `{ parseConfig: { ocr: true } }` produces OCR text through the converter, given an image-or-OCR output mode).\n\n```ts\nimport { OfficeConverter } from 'officeparser';\n\n// Minimal usage\nconst { value: markdown } = await OfficeConverter.convert('report.docx', 'md');\n\n// With config\nconst { value: html, messages } = await OfficeConverter.convert('data.xlsx', 'html', {\n    parseConfig: {\n        ignoreNotes: true,\n        newlineDelimiter: '\\n\\n',\n    },\n    generatorConfig: {\n        includeFormatting: true,\n        styleMap: [\n            {\n                selector: { attributes: { style: { value: 'Header', operator: '~=' } } },\n                output: { tag: 'h2', classes: ['data-header'] }\n            }\n        ]\n    },\n    onWarning: (issue) => console.warn(`[${issue.code}] ${issue.message}`)\n});\n```\n\n> [!IMPORTANT]\n> The `OfficeConverterConfig` shape uses **nested** `parseConfig` and `generatorConfig` sub-objects.\n> Do **not** put parser or generator options at the top level; only `onWarning` lives there.\n\n---\n\n## OfficeTemplate: Mail-Merge / Document Generation\n\n`OfficeTemplate.render()` (alias `renderTemplate`) fills a **DOCX template**'s `{{placeholder}}` tags from your data and returns a new `.docx`. It is not parsing or conversion: the template is copied and only the placeholders are substituted, so **all of the template's formatting, layout and structure are preserved**. Give it one data object for one document, or an array for a batch (one document per entry, a classic mail-merge). Think of it as a zero-dependency take on Adobe's Document Generation API.\n\n```ts\nimport { OfficeTemplate } from 'officeparser';\nimport { writeFileSync } from 'fs';\n\n// One document.\nconst bytes = await OfficeTemplate.render('invoice-template.docx', {\n    data: { name: 'Acme Corp', amount: '$1,250.00', due: '2026-10-01' },\n});\nwriteFileSync('invoice-acme.docx', bytes); // Uint8Array\n\n// A batch: one .docx per row.\nconst docs = await OfficeTemplate.render('invoice-template.docx', {\n    data: [\n        { name: 'Acme Corp', amount: '$1,250.00' },\n        { name: 'Globex',    amount: '$980.00'   },\n    ],\n});\ndocs.forEach((d, i) => writeFileSync(`invoice-${i}.docx`, d));\n```\n\n- **Run-aware.** Word often splits a typed `{{name}}` across several runs (`{{`, `na`, `me}}`); it is filled anyway, and a value takes the **formatting of the run its placeholder sat in** (a bold `{{amount}}` renders bold).\n- **Everywhere text lives.** Placeholders in the body, headers, footers, footnotes/endnotes and comments are all filled. Values may contain `\\n` (rendered as line breaks).\n- **Placeholder names** are Unicode letters and digits plus `_`, `.`, `-` (e.g. `{{invoice.total}}`, `{{customer-name}}`). A name containing a space or other punctuation is not recognized and is left as literal text, so surrounding prose between the delimiters is never mistaken for a field.\n- **Deterministic** output (pinned zip timestamps): the same template + data always renders byte-identical bytes.\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `data` | `TemplateData \\| TemplateData[]` | (required) | Field values. One object is one document; an array is one document per entry |\n| `delimiters` | `{ start: string; end: string }` | `{{ }}` | Placeholder delimiters |\n| `onMissing` | `'keep' \\| 'empty' \\| 'error'` | `'keep'` | A placeholder with no matching field: leave it, blank it, or reject with `TEMPLATE_FIELD_MISSING`. A field present but `null`/`undefined` always renders empty |\n| `password` | `string` | (none) | Decrypt the template first, if it is itself password-protected |\n\nOnly DOCX is supported today (other OOXML/ODF formats will follow); a non-DOCX template rejects with `TEMPLATE_UNSUPPORTED_FORMAT`.\n\n---\n\n## Native RAG Chunking\n\n`officeParser` provides native document chunking for Retrieval-Augmented Generation (RAG) pipelines with three strategies:\n\n### Strategy 1: Document Structure (Default)\nSplits at natural AST boundaries (paragraphs, headings, pages, slides, sheets). Preserves logical flow.\n\n```ts\nconst { value: chunks } = await OfficeConverter.convert('report.docx', 'chunks', {\n    generatorConfig: {\n        chunksConfig: {\n            strategy: 'document-structure',\n            splitBy: 'heading',    // 'paragraph' | 'heading' | 'page' | 'slide' | 'sheet'\n            maxChunkSize: 1500,\n            tableSplitStrategy: 'row', // repeats header row in every chunk, ideal for RAG\n        }\n    }\n});\n```\n\n### Strategy 2: Fixed-Size (Recursive)\nSplits by character count with overlap. Equivalent to LangChain's `RecursiveCharacterTextSplitter`.\n\n```ts\nconst { value: chunks } = await OfficeConverter.convert('report.docx', 'chunks', {\n    generatorConfig: {\n        chunksConfig: {\n            strategy: 'fixed-size',\n            chunkSize: 1000,\n            chunkOverlap: 200,\n        }\n    }\n});\nconsole.log(`Generated ${chunks.length} chunks`);\n```\n\n### Strategy 3: Semantic\nUses cosine similarity between sentence embeddings to find topic boundaries. Requires you to provide an `embeddingFunction`.\n\n```ts\nimport OpenAI from 'openai';\nconst openai = new OpenAI();\n\nconst { value: chunks } = await OfficeConverter.convert('report.docx', 'chunks', {\n    generatorConfig: {\n        chunksConfig: {\n            strategy: 'semantic',\n            embeddingFunction: async (text) => {\n                const res = await openai.embeddings.create({\n                    input: text, model: 'text-embedding-3-small'\n                });\n                return res.data[0].embedding;\n            },\n            similarityThreshold: 0.8,\n            maxChunkSize: 2000,\n        }\n    }\n});\n```\n\n### The `OfficeChunk` Object\n\n`generate(ast, 'chunks')` (and `ast.to('chunks')`) resolves to a real `OfficeChunk[]` **array**, not a JSON string - serialize it to JSON/JSONL yourself if your pipeline needs that.\n\nEvery chunk contains text and rich metadata for citations and filtered retrieval:\n\n```ts\ninterface OfficeChunk {\n    text: string;\n    /** Rich metadata for filtered retrieval */\n    metadata: {\n        sourceType: string;       // e.g., 'docx', 'pdf'\n        pageNumber?: number;      // (PDF only)\n        slideNumber?: number;     // (PPTX only)\n        sheetName?: string;       // (XLSX only)\n        closestHeading?: string;  // Nearest heading above this chunk\n        isTableChunk?: boolean;   // True if part of a split table\n    };\n    startIndex?: number;          // Character offset (if addStartIndex: true)\n    endIndex?: number;            // End character offset (if addStartIndex: true)\n}\n```\n\n---\n\n## The AST Structure\n\n`OfficeParserAST` is a format-agnostic document representation:\n\n```text\nOfficeParserAST\n├── type: 'docx' | 'pdf' | 'xlsx' | 'csv' | 'md' | 'epub' | ...  (13 formats)\n├── metadata: { author, title, created, modified, keywords, customProperties, nativeProperties, styleMap, ... }\n├── content: [ OfficeContentNode ]\n│   ├── type: 'paragraph' | 'heading' | 'table' | 'list' | 'image' | 'chart' | 'comment' | 'admonition' | 'embed' | 'definitionList' | ...\n│   ├── text: string  (concatenated text of node + all descendants)\n│   ├── children: [ OfficeContentNode ]  (recursive structural children)\n│   ├── notes: [ OfficeContentNode ]     (footnotes/endnotes/slide notes attached to this node)\n│   ├── comments: [ OfficeContentNode ] (inline comments attached to this node)\n│   ├── formatting: { bold, italic, underline, color, size, font, alignment, ... }\n│   └── metadata: { level, listId, row, col, rowSpan, colSpan, backgroundColor, style, ... }\n├── auxiliary?: OfficeAuxiliaryContent   (out-of-band layout elements)\n│   ├── headers?: OfficeContentNode[]   (DOCX, PDF top band, ODT master pages)\n│   ├── footers?: OfficeContentNode[]   (DOCX, PDF bottom band, ODT master pages)\n│   ├── slideMasters?: OfficeContentNode[] (PPTX slide masters)\n│   └── outline?: OfficeContentNode[]   (PDF bookmark outline)\n├── attachments: [ OfficeAttachment ]  (populated when extractAttachments: true)\n│   ├── type: 'image' | 'chart'\n│   ├── name: string\n│   ├── mimeType: string\n│   ├── data: string  (Base64)\n│   ├── ocrText?: string  (if ocr: true AND extractAttachments: true)\n│   └── chartData?: { title, dataSets, labels }\n├── warnings: OfficeIssue[]  (non-fatal issues from the parsing phase)\n├── config: OfficeParserConfig  (the resolved parse config; `.to()` inherits newlineDelimiter/onWarning from it)\n└── to(format, config?)  (format: 'html'|'md'|'text'|'csv'|'rtf'|'pdf'|'docx'|'odt'|'epub'|'chunks', returns { value, messages })\n```\n\n### `OfficeIssue`: Warning / Error Object\n\nAll warnings and errors (from both parsing and generation) use this shape:\n\n```ts\ninterface OfficeIssue {\n    type: 'warning' | 'info' | 'error';\n    code: OfficeWarningType | OfficeErrorType;  // typed enum, e.g. 'OCR_FAILED'\n    message: string;\n    node?: OfficeContentNode;  // the node that triggered the issue, if any\n    details?: any;             // original error or extra context\n}\n```\n\nThrown errors carry the same object on `error.officeIssue`, so a failed parse is identified by\nthe same stable `code` you would branch on for a warning, rather than by matching message text:\n\n```js\ntry {\n    const ast = await officeParser.parseOffice(buffer, { fileType: 'docx' });\n} catch (err) {\n    switch (err.officeIssue?.code) {\n        case 'ZIP_NO_ENTRIES_FOUND':  // not a ZIP archive at all\n        case 'ZIP_TRUNCATED':         // cut off in transfer, entries incomplete\n        case 'REQUIRED_PART_MISSING': // readable ZIP, but not the format it claims\n            console.error('Unusable file:', err.officeIssue.message);\n            break;\n        default:\n            throw err;\n    }\n}\n```\n\n> [!IMPORTANT]\n> **A corrupt file throws; it does not parse as an empty document.** If an archive is not\n> readable, is truncated, or is missing the part its format requires (`word/document.xml`,\n> `xl/workbook.xml`, `ppt/presentation.xml`, ODF `content.xml`, the EPUB OPF), parsing rejects\n> with one of the codes above. An empty result therefore means the document really is empty.\n> Files that are legitimately empty still parse, and say so through `onWarning` /\n> `ast.warnings` (`NO_WORKSHEETS_FOUND` for a chartsheet-only workbook, `NO_SLIDES_FOUND` for a\n> presentation with no slides).\n\n#### Warning codes (`type: 'warning' | 'info'`, delivered to `onWarning` and collected in `ast.warnings`)\n\nThese never throw; they report a degraded-but-successful outcome you may branch on by `code`.\n\n| Code | Phase | Meaning / what to do |\n|---|---|---|\n| `OCR_REQUIRES_ATTACHMENTS` | parse | `ocr: true` without `extractAttachments: true`; no OCR ran. Set both. |\n| `PDF_NO_TEXT_EXTRACTED` | parse | A PDF yielded ~no text (likely scanned). Set `ocr: true` + `extractAttachments: true`. |\n| `PDF_STRUCT_TREE_UNRELIABLE` | parse | PDF tag tree absent/incomplete; structure recovered geometrically. |\n| `PDF_TEXT_ENCODING_SUSPECT` | parse | PDF glyphs mostly unmappable (broken ToUnicode); text may be garbage. Consider OCR. |\n| `PDF_OUTLINE_TRUNCATED` | parse | Bookmark outline hit the depth/size cap; `ast.auxiliary.outline` is partial. |\n| `PDF_WORKER_MISSING` / `PDF_WORKER_FALLBACK` | parse | The pdf.js worker could not be loaded / a fallback was used (set `pdfWorkerSrc`). |\n| `NO_WORKSHEETS_FOUND` / `NO_SLIDES_FOUND` | parse | A legitimately empty workbook/presentation. |\n| `TABLE_CELL_LIMIT_EXCEEDED` | parse | A table exceeded `decompressionLimits.maxTableCells`; it was clamped. |\n| `IMAGE_EXTRACTION_FAILED` / `IMAGE_PROCESSING_FAILED` / `ATTACHMENT_EXTRACTION_FAILED` | parse | An image/attachment could not be extracted or decoded; it was skipped or degraded. |\n| `ANNOTATION_EXTRACTION_FAILED` / `CHART_DATA_EXTRACTION_FAILED` | parse | A PDF annotation / a chart's data could not be read. |\n| `OCR_FAILED` | parse | OCR ran but failed for an image (see `details`). |\n| `FILE_TYPE_DETECTION_FAILED` / `BUFFER_TYPE_MISMATCH` | parse | Type could not be sniffed / disagreed with the `fileType` hint. |\n| `PASSWORD_REQUIRED` / `PASSWORD_INCORRECT` | parse | Encrypted input; supply `password`/`onPassword` (these also throw when parsing cannot continue). |\n| `UNRECOGNIZED_CONFIG_OPTION` | config | A config key this version does not know (often a typo or a removed/renamed option); it had no effect. |\n| `CONTENT_NOT_REPRESENTABLE` | generate | A node type has no faithful form in the target format and was downgraded or omitted (e.g. math/embeds in DOCX/ODT, a table-less document to CSV). |\n| `METADATA_NOT_REPRESENTABLE` | generate | A metadata field could not be represented in the target format. |\n| `IMAGE_NOT_INLINED` | generate | An image over `maxInlineImageBytes` was referenced by name instead of inlined (Markdown / fragment HTML). |\n| `PDF_GENERATION_FAILED` | generate | PDF generation failed (e.g. Puppeteer missing for `engine: 'html'`). |\n| `INVALID_STYLE_MAPPING` / `INVALID_STYLE_MAP_TAG` | generate | A `styleMap` entry/tag was invalid and ignored. |\n| `TEMPLATE_UNSUPPORTED_FORMAT` / `TEMPLATE_FIELD_MISSING` | template | The template format is unsupported / a `{{field}}` had no value under `onMissing: 'error'`. |\n| `PAGE_LOAD_FAILED` | parse | A PDF page could not be processed and was skipped (partial content). |\n| `SHEET_RANGE_NOT_FOUND` | generate | A `csvConfig.sheets` range matched no sheet, so CSV output is empty. |\n| `EMPTY_CHUNK_GENERATED` / `WHITESPACE_NODE_SKIPPED` / `BROWSER_GENERATION_LIMITATION` / `PERFORMANCE_TIP` / `DEPENDENCY_LOAD_FAILED` | generate | Diagnostic/informational notes from the chunking and PDF generators. |\n\nThe full enum lives in `OfficeWarningType` / `OfficeErrorType` (`src/types.ts`); the error codes used in the `catch` above are the `OfficeErrorType` members.\n\n---\n\n## Per-Format Capability Matrix\n\nWhat each parser extracts differs by format, because the source formats themselves differ. This table\nis the authoritative reference; the option docs point back to it. `Y` = extracted by default (subject to\nthe relevant `ignore*`/`extractAttachments` flag), `–` = the format has no such construct or it is not\nextracted (the matching `ignore*` flag is then a no-op).\n\n| Input | Comments (`node.comments`) | Notes (`node.notes`) | Headers/footers (`ast.auxiliary`) | Slide masters | Images (needs `extractAttachments`) | Charts | Tables (colSpan/rowSpan) |\n|---|---|---|---|---|---|---|---|\n| DOCX | Y | footnotes/endnotes | Y | – | Y | Y | Y |\n| XLSX | Y | – | – | – | Y | Y | grid |\n| PPTX | Y | speaker notes | – | Y | Y | Y | Y |\n| ODT  | Y (in text) | footnotes/endnotes | Y (master pages) | – | Y | Y | Y |\n| ODS  | Y (cell notes) | – | – | – | Y | Y | grid |\n| ODP  | Y (page) | speaker notes | – | – (ODP masters not extracted) | Y | Y | Y |\n| ODG  | Y (page) | – | – | – | Y | – | Y |\n| PDF  | – | footnotes/endnotes (tagged) | Y (top/bottom bands) | – | Y | – | Y (spans: tagged only) |\n| RTF  | – | footnotes/endnotes | – (dropped) | – | Y | – | Y |\n| HTML | – | footnotes/endnotes | – | – | Y (`data:` only) | – | Y |\n| MD   | – | footnotes/endnotes | – | – | Y (`data:` only) | – | Y (HTML-table fallback) |\n| CSV  | `#`-rows become `comment` nodes* | – | – | – | – | – | rows |\n| EPUB | – | footnotes/endnotes | – | – | Y | – | Y |\n\nNotes: comments land on `node.comments[]` (with `author`/`date`) except CSV, whose leading-`#` rows\nbecome top-level `comment` nodes and are *not* governed by `ignoreComments`. `ignoreNotes` /\n`ignoreComments` / `ignoreHeadersAndFooters` / `ignoreSlideMasters` each remove the corresponding\ncolumn and are a no-op wherever it shows `–`. OCR (`ocr: true`) recognizes text from any extracted\nimage and therefore also needs `extractAttachments: true`.\n\n---\n\n## Deep Dive: Document Components\n\n### 1. Lists\n\n```text\nList Node\n├── type: 'list'\n├── metadata: {\n│       listId: '1',          // items with the same listId belong to one logical list\n│       listType: 'ordered' | 'unordered',\n│       indentation: 0,       // nesting level (0-based)\n│       itemIndex: 0,         // sequential position within the list level\n│       paragraphIndentation: { left, hanging, right, firstLine }\n│   }\n└── children: [ Text content ]\n```\n\n> [!TIP]\n> Even if a list is interrupted by a regular paragraph, `itemIndex` keeps incrementing for the same `listId`, so numbering stays correct.\n\n### 2. Tables\n\nTables follow a strict `table → row → cell` hierarchy:\n\n```text\nTable Node (type: 'table')\n└── children: Row Nodes (type: 'row')\n    └── children: Cell Nodes (type: 'cell')\n        ├── metadata: { row, col, rowSpan?, colSpan? }\n        └── children: [ Paragraph | List | Table | ... ]\n```\n\n- `row` / `col`: zero-based grid position\n- `rowSpan` / `colSpan`: merged cells (DOCX, ODF, HTML, Markdown HTML-tables, and tagged PDF)\n- Cells can contain nested tables\n\n> [!NOTE]\n> **Header rows.** A header row is flagged on its cells' metadata (`style: 'header'`, or `isHeader`),\n> set by the parsers that mark one (DOCX `w:tblHeader`, ODF `table:table-header-rows`, HTML `<th>`/\n> `<thead>`, tagged-PDF `TH`); generators read it through one shared heuristic (a marked row, or an\n> all-bold first row). One format-imposed asymmetry: a **Markdown** table always renders a header row\n> (the GFM `| --- |` separator is mandatory syntax), whereas **HTML** emits `<thead>` only for a\n> detected header. So a table with no real header prints a header in Markdown output but not in HTML.\n\n### 3. Images & OCR\n\n```text\nImage Node (type: 'image')\n├── metadata: { attachmentName: 'img1.png', altText: '...' }\n└── → Attachment: { data: 'base64...', ocrText: '...' }\n```\n\n- Set `extractAttachments: true` to populate `attachment.data`\n- Set `ocr: true` (requires `extractAttachments: true`) to populate `ocrText`\n\n### 4. Charts\n\n```text\nChart Node (type: 'chart')\n├── metadata: { attachmentName: 'chart1.xml' }\n└── → Attachment: { chartData: { title, dataSets, labels } }\n```\n\n### 5. Text Formatting\n\n```ts\nformatting: {\n    bold?: boolean\n    italic?: boolean\n    underline?: boolean\n    strikethrough?: boolean\n    color?: string          // '#RRGGBB'\n    backgroundColor?: string\n    size?: string           // e.g. '12pt'\n    font?: string\n    subscript?: boolean\n    superscript?: boolean\n    alignment?: 'left' | 'center' | 'right' | 'justify'\n}\n```\n\n> [!NOTE]\n> On a **content node**, an absent flag and `false` mean the same thing — the flag is simply not\n> applied. On **`ast.metadata.styleMap`**, they differ: an absent flag means the style says nothing\n> about that property (so it inherits), while `false` means the style explicitly turns it off\n> (ODF's `fo:font-weight=\"normal\"`, DOCX's `<w:b w:val=\"0\"/>`). Code resolving inheritance itself\n> must test `=== undefined`, not truthiness, or it will treat \"explicitly off\" as \"unspecified\".\n\n### 6. Break Nodes (DOCX and ODF)\n\nWhen `includeBreakNodes: true`, break elements appear as nodes:\n\n```text\nBreak Node (type: 'break')\n└── metadata: {\n        breakType: 'textWrapping' | 'page' | 'column' | 'lastRenderedPage' | 'carriageReturn' | 'thematic',\n        clear?: 'all' | 'left' | 'none' | 'right'\n    }\n```\n\n> [!NOTE]\n> Break nodes have no `text` property, but `ast.to('text')` automatically converts them to the configured newline delimiter.\n\n> [!NOTE]\n> `includeBreakNodes` gates DOCX/ODF only (where a break is otherwise invisible layout). **HTML and\n> Markdown always emit break nodes regardless of the flag**, because a break is explicit content there:\n> a `<br>`/hard line break becomes a `carriageReturn` break, and `<hr>`/`---` a `thematic` break (a\n> Markdown `\\f`-style page break maps to `page`).\n\n> [!NOTE]\n> DOCX writes breaks inline (`w:br`/`w:cr`), so they land as children of the paragraph. ODF instead\n> carries page and column breaks on the paragraph *style* (`fo:break-before`/`fo:break-after`), so those\n> are emitted as siblings around the paragraph rather than inside it. `<text:soft-page-break/>` maps onto\n> `lastRenderedPage`, the same type as DOCX's `w:lastRenderedPageBreak`.\n\n### 6b. Equations\n\nEquations are extracted from every format that can carry them and normalized to **LaTeX**, so a\nformula means the same thing whichever format it arrived in:\n\n| Source format | Markup in the file |\n|---|---|\n| DOCX, PPTX | OOXML `<m:oMath>` / `<m:oMathPara>` |\n| ODT, ODP, ODS | MathML inside the embedded formula object |\n| HTML, EPUB | native MathML `<math>` |\n| Markdown | `$inline$` / `$$block$$` |\n\nThey all land as the same node:\n\n```text\nCode Node (type: 'code')\n├── text: '\\\\frac{1}{2}'          // LaTeX, whatever the source markup was\n└── metadata: { math: 'inline' | 'block' }\n```\n\nFractions, sub/superscripts, radicals, delimiters, n-ary operators (sums, integrals), named\nfunctions, accents, bars, matrices and math alphabets (`ℝ`, `𝒜`, …) are all preserved. When a\ndocument supplies its own TeX source in an `<annotation encoding=\"application/x-tex\">`, that is\nused verbatim in preference to anything reconstructed from the presentation markup.\n\n> [!NOTE]\n> Equation text is *structure*, not prose: a fraction whose numerator and denominator are simply\n> concatenated reads as a different number rather than as obviously-missing content. Consumers that\n> index document text should treat `code` nodes carrying `math` as opaque LaTeX rather than\n> splitting them as words.\n\n**On generation**, an equation's fate depends on the target: HTML and Markdown keep it as LaTeX (a\n`$…$`/`$$…$$` delimited block or a `data-math` attribute); DOCX and ODT downgrade it to its LaTeX text\nand emit a `CONTENT_NOT_REPRESENTABLE` warning (no native OMML/ODF-math is written); plain text, RTF and\nthe PDF engines render the LaTeX string as-is without a warning. So the LaTeX always survives, but only\nHTML/Markdown round-trip it as math.\n\n### 7. Document Metadata\n\n```ts\nast.metadata = {\n    author?: string\n    title?: string\n    created?: Date\n    modified?: Date\n    description?: string\n    keywords?: string                            // NEW: Keywords from document properties\n    customProperties?: Record<string, any>       // User-defined metadata from the document\n    nativeProperties?: Record<string, any>       // NEW: All format-specific raw metadata\n    styleMap?: Record<string, TextFormatting>    // Named styles → formatting definitions\n    formatting?: TextFormatting                  // Document-wide defaults\n}\n```\n\n**Accessing native properties (format-specific metadata):**\n```js\nconst ast = await officeParser.parseOffice('contract.docx');\nconsole.log(ast.metadata.nativeProperties);\n// DOCX: { Pages: 5, Application: 'Microsoft Word' }\n// HTML: { description: 'My page', 'og:title': 'Title' }\n// PDF:  { Title: 'Report', XMP: { ... } }\n```\n\n### 8. Admonitions, Embeds & Definition Lists\n\n```text\nAdmonition Node (type: 'admonition')\n├── metadata: { admonitionType: 'note' | 'tip' | 'important' | 'warning' | 'caution', title?: string }\n└── children: [ Paragraph | List | ... ]   (block content)\n\nEmbed Node (type: 'embed')\n└── metadata: { embedType: 'youtube' | 'iframe', videoId?: string, url?: string, width?: string, height?: string, align?: string }\n\nDefinition List Node (type: 'definitionList')\n└── children:\n    ├── Definition Term (type: 'definitionTerm')\n    └── Definition Description (type: 'definitionDescription')\n```\n\n- `admonition` round-trips through both Markdown (`> [!NOTE]` / `:::note ... :::`) and HTML (`<div class=\"admonition admonition-note\" data-type=\"note\">`)\n- `embed` models YouTube videos and generic iframes. Markdown form is selected by `mdConfig.dialect.embeds`: `'html'` (default; the `<div data-youtube-video>` / `<iframe>` block), `'directive'` (a `::youtube[…]{…}` / `::embed[…]{…}` leaf directive), `'link'`, or `'thumbnail'` (YouTube-only clickable preview). A generic iframe is captured only under `htmlParserConfig.preserveIframes` (the trust input) and can be emitted as an inert click-to-load placeholder via `htmlConfig.gatedEmbeds`. The `'directive'` form is an editor round-trip format, not GitHub-rendered\n- Abbreviations (`*[HTML]: Hypertext Markup Language`) are stored as `TextMetadata.abbreviationTitle` on the abbreviated text node rather than as a separate node type\n\n---\n\n## Markdown Dialect Support\n\nBeyond CommonMark/GFM basics, `MarkdownParser`/`MarkdownGenerator` support an extended dialect aimed at\nfull-fidelity round-tripping with rich Markdown editors. Every construct below parses to a first-class\nAST node/metadata field and regenerates back to the canonical syntax shown, so `.md → AST → .md` is\nidempotent and `.md → AST → HTML → AST → .md` survives unchanged.\n\n> Markdown-input parsing options that are not dialect toggles live on `htmlParserConfig` (Markdown\n> shares the HTML parser for embeds): `preserveIframes` and `embedFolkForms` govern raw `<iframe>`\n> blocks and folk embed forms encountered in `.md`. There is no separate `mdParserConfig`.\n\n| Feature | Markdown syntax | AST representation |\n|---|---|---|\n| Task lists (GFM) | `- [x] Done` / `- [ ] Todo` | `ListMetadata.isTask` / `.checked` |\n| Admonitions | `> [!NOTE]` (also accepts GLFM `:::note ... :::` on import) | `type: 'admonition'`, `AdmonitionMetadata` |\n| Footnotes | `Text[^1]` + `[^1]: Definition` | `type: 'note'`, keyed by footnote id |\n| Definition lists | `Term\\n: Definition` | `type: 'definitionList'` / `'definitionTerm'` / `'definitionDescription'` |\n| Abbreviations | `*[HTML]: Hypertext Markup Language` | `TextMetadata.abbreviationTitle` |\n| Attribute lists | `![alt](img.png){width=50% .centered}` | `ImageMetadata.width` / `.align`, `TableMetadata.align` |\n| Citations | `[@smith2024]` | `TextMetadata.citationKey` |\n| Wikilinks | `[[Page]]` / `[[Page\\|Alias]]` | `TextMetadata.wikilink`, `.link`, `.linkType` |\n| Highlight | `==text==` | `TextMetadata.backgroundColor` |\n| Link/image titles | `[text](url \"Title\")` / `![alt](img.png \"Title\")` | `TextMetadata.title` / `ImageMetadata.title` |\n| Inline/block math | `$E=mc^2$` / `` $$...$$ `` | `type: 'code'`, `CodeMetadata.math` (`'inline' \\| 'block'`) |\n| Embeds | `::youtube[Label]{id=… width=… align=…}` / `::embed[Label]{src=… …}` (leaf directive; see `mdConfig.dialect.embeds`) | `type: 'embed'`, `EmbedMetadata` |\n| Frontmatter arrays | `tags: [a, b]` or `tags: [\"a\",\"b\"]` | Real array in `metadata.customProperties`/`nativeProperties` |\n| MDX components (import-only) | `<Component prop=\"x\">...</Component>` | Stripped; inner Markdown is kept. Never generated back. |\n\n> [!NOTE]\n> MDX/JSX stripping is one-directional (parse-only) — officeParser never authors JSX back into Markdown.\n> Wikilink enable/disable and citekey→bibliography resolution are application-level concerns; officeParser\n> always parses/generates the syntax itself.\n\nThe same round-trip fidelity extends to HTML, so content saved from a rich-text editor survives a\nsave→reload cycle:\n\n| HTML attribute | AST field | Notes |\n|---|---|---|\n| `data-width` / `data-align` / inline `style=\"width:…\"` on `<img>` | `ImageMetadata.width` / `.align` | |\n| `data-align` on `<table>` | `TableMetadata.align` | Emitted/parsed as per-column GFM markers (`:---`, `:---:`, `---:`); alignment rides `CellMetadata.align` |\n| `title` on `<a>` / `<img>` | `TextMetadata.title` / `ImageMetadata.title` | Survives both directions (`[text](url \"Title\")` in Markdown) |\n| `colspan` / `rowspan` on `<td>`/`<th>` | `CellMetadata.colSpan` / `.rowSpan` | Previously dropped on HTML import — merged cells now survive a save→reload cycle |\n| `<div data-youtube-video=\"ID\">` / `<iframe src=\"...youtube.com...\">` | `type: 'embed'` | |\n| `<ul data-type=\"taskList\">` / `<li data-checked>` | `ListMetadata.isTask` / `.checked` | |\n\n---\n\n## EPUB Support\n\nEPUB files are ZIP archives of XHTML content plus an OPF manifest — `EpubParser` unzips the archive,\nresolves the spine's reading order from `content.opf`, and parses each XHTML document through the\nexisting `HtmlParser`, so EPUB content shares the same AST shape (and the same Markdown-dialect\nfidelity above) as every other format. Dublin Core metadata (`dc:title`, `dc:creator`, `dc:description`,\n`dc:subject`, `dc:date`, `dc:publisher`, `dc:language`, `dc:identifier`) maps into `ast.metadata` /\n`ast.metadata.nativeProperties`, and cover art is exposed via `metadata.customProperties.coverImageName`.\n\n`EpubGenerator` renders the AST through `HtmlGenerator` and packages the result as a minimal, valid\nEPUB 3 (`mimetype`, `META-INF/container.xml`, an OPF manifest, a nav document, and one XHTML chapter).\n\n> [!IMPORTANT]\n> **Pass `extractAttachments: true` when converting to or from EPUB if the document has images.**\n> Without it, the parser never pulls embedded image bytes out of the source document, so there is\n> nothing for the EPUB generator to package — images silently disappear even though everything else\n> converts correctly. Images are packaged as real zip entries (`OEBPS/images/...`) declared in the OPF\n> manifest, not `data:` URIs — most EPUB reading systems do not render `data:` URIs in image `src`.\n>\n> This only matters for the two-step `OfficeParser.parseOffice()` → `OfficeGenerator.generate()` API\n> and the CLI. [`OfficeConverter.convert()`](#officeconverter-one-step-api) enables `extractAttachments`\n> automatically unless you explicitly set `generatorConfig.includeImages: false`.\n>\n> ```bash\n> npx officeparser book.docx --extractAttachments --to=epub --output=book.epub\n> ```\n\n---\n\n## Performance Highlights\n\nKey internal optimizations shipped in recent versions:\n\n- **OpenOffice (ODP)**: Up to **23× faster** parsing via optimized XML pre-parsing and style caching\n- **Excel Memory**: Resolved O(n) memory overhead on large sparse spreadsheets using iterative stream-based parsing\n- **RTF Parser**: Rewrote string accumulation loop to eliminate O(n²) bottleneck in large files\n- **Table Fidelity (DOCX)**: Native support for vertical cell merging (`vMerge`) and horizontal spanning (`gridSpan`)\n\n---\n\n## Advanced AST Usage\n\n### Extract all headings\n```js\nconst headings = ast.content.filter(n => n.type === 'heading' && n.metadata?.level === 1);\nconsole.log(headings.map(h => h.text));\n```\n\n### Extract comments\n```ts\n// Comments can be attached to any nested node, so we must traverse recursively\nconst printComments = (nodes: OfficeContentNode[]) => {\n    nodes.forEach(node => {\n        if (node.comments) {\n            node.comments.forEach(c => {\n                console.log(`Comment by ${c.metadata?.author}: ${c.text}`);\n            });\n        }\n        if (node.children) {\n            printComments(node.children);\n        }\n    });\n};\n\nprintComments(ast.content);\n```\n\nSet `ignoreComments: true` to skip extraction.\n\n### Extract footnotes, endnotes & slide notes\n```ts\n// Slide speaker notes (PPTX) live on the slide node itself\nconst slide = ast.content.find(n => n.type === 'slide');\nconsole.log(slide?.notes?.map(n => n.text));\n\n// Footnotes and endnotes (DOCX, ODT, RTF, PDF, HTML, Markdown, EPUB) can be deeply nested, so we traverse recursively:\nconst printNotes = (nodes: OfficeContentNode[]) => {\n    nodes.forEach(node => {\n        if (node.notes) {\n            node.notes.forEach(note => console.log(note.text));\n        }\n        if (node.children) {\n            printNotes(node.children);\n        }\n    });\n};\n\nprintNotes(ast.content);\n```\n\n> [!IMPORTANT]\n> `putNotesAtLast` was **removed in v8**. Notes are always attached via `node.notes`.\n\n### Access headers, footers & slide masters\n```ts\n// These are NOT in ast.content; use ast.auxiliary\nconsole.log(ast.auxiliary?.headers?.map(h => h.text));   // DOCX headers\nconsole.log(ast.auxiliary?.footers?.map(f => f.text));   // DOCX footers\nconsole.log(ast.auxiliary?.slideMasters?.length);         // PPTX slide masters\n```\n\nSet `ignoreHeadersAndFooters: true` or `ignoreSlideMasters: true` to skip extraction.\n\n### Extract images with OCR text\n```js\nconst ast = await officeParser.parseOffice('report.docx', { extractAttachments: true, ocr: true });\nast.attachments.filter(a => a.mimeType?.startsWith('image/')).forEach(img => {\n    console.log(`${img.name}: ${img.ocrText ?? 'no OCR'}`);\n});\n```\n\n### Extract tables to CSV manually\n```js\nast.content.filter(n => n.type === 'table').forEach((table, i) => {\n    const csv = table.children\n        .filter(r => r.type === 'row')\n        .map(r => r.children.filter(c => c.type === 'cell')\n            .map(c => `\"${c.text.replace(/\"/g, '\"\"')}\"`)\n            .join(','))\n        .join('\\n');\n    console.log(`Table ${i + 1}:\\n${csv}`);\n});\n```\n\n### Find all bold text runs\n```js\nfunction findBold(nodes) {\n    return nodes.flatMap(n => [\n        ...(n.type === 'text' && n.formatting?.bold ? [n.text] : []),\n        ...(n.children ? findBold(n.children) : [])\n    ]);\n}\nconsole.log(findBold(ast.content));\n```\n\n### Extract footnotes / endnotes\n```js\nfunction extractNotes(nodes) {\n    return nodes.flatMap(n => [\n        ...(n.type === 'note' ? [{ id: n.metadata.noteId, text: n.text, type: n.metadata.noteType }] : []),\n        ...(n.children ? extractNotes(n.children) : [])\n    ]);\n}\nconsole.log(extractNotes(ast.content));\n```\n\n### Search for a term (TypeScript)\n```ts\nimport { OfficeParser } from 'officeparser';\n\nasync function contains(filePath: string, term: string): Promise<boolean> {\n    const ast = await OfficeParser.parseOffice(filePath);\n    return (await ast.to('text')).value.includes(term);\n}\n```\n\n---\n\n## Configuration Reference\n\n### OfficeParserConfig\n\nPass as the second argument to `parseOffice(file, config)`.\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `newlineDelimiter` | `string` | `'\\n'` | Joins multi-line text inside the AST's pre-flattened `.text` (RTF table cells, chart text, PDF page text); also the default for `textConfig.newlineDelimiter` in `.to('text')` when that is not set explicitly. Not read by the Word parser |\n| `password` | `string` | `''` | Password for a password-protected document. Applies to every encryptable format: PDF, encrypted OOXML (`.docx`/`.xlsx`/`.pptx`, ECMA-376 agile or standard AES), and encrypted ODF (`.odt`/`.ods`/`.odp`/`.odg`, AES-CBC with PBKDF2). A missing password rejects with `PASSWORD_REQUIRED`, a wrong one with `PASSWORD_INCORRECT`. Ignored for unencrypted files. *ODF note:* LibreOffice 24.8+ defaults to AES-256-GCM with Argon2id key derivation (\"wholesome encryption\"), which is not supported and rejects with `DOCUMENT_DECRYPTION_FAILED`; re-save with the classic AES-CBC/PBKDF2 scheme (or an earlier LibreOffice) to parse it |\n| `onPassword` | `(reason: 'required' \\| 'incorrect') => string \\| undefined \\| Promise<...>` | (none) | Called when an encrypted document needs a password `password` did not satisfy, so it can be supplied lazily or interactively (prompt, vault). Return a password to retry (capped), or `undefined` to reject as above. Works for every encryptable format (PDF/OOXML/ODF); mirrors pdf.js's `onPassword` |\n| `ignoreNotes` | `boolean` | `false` | Ignore footnotes/endnotes (DOCX, ODT, RTF, PDF, HTML, Markdown, EPUB) and speaker notes (PPTX/ODP). See the [capability matrix](#per-format-capability-matrix) |\n| `ignoreComments` | `boolean` | `false` | Ignore comments/annotations, attached by default via `node.comments[]`. Applies to DOCX, XLSX, PPTX and every ODF type (ODT/ODS/ODP/ODG). See the [capability matrix](#per-format-capability-matrix) |\n| `ignoreHeadersAndFooters` | `boolean` | `false` | Skip headers & footers (populated in `ast.auxiliary.headers/footers` by default). Extracted for DOCX, PDF and ODT only; a no-op for ODS/ODP/ODG, XLSX, PPTX and RTF. See the [capability matrix](#per-format-capability-matrix) |\n| `ignoreSlideMasters` | `boolean` | `false` | Skip PPTX slide masters (populated in `ast.auxiliary.slideMasters` by default). PPTX only; ODP masters are not extracted |\n| `extractAttachments` | `boolean` | `false` | Populate `ast.attachments` with Base64 images/charts |\n| `ocr` | `boolean` | `false` | Run Tesseract OCR on images (requires `extractAttachments: true`) |\n| `ocrConfig` | `OcrConfig` | see below | OCR settings (populated defaults: `language: 'eng'`, `preserveLayout: true`, worker/timeout defaults). See the [OCR section](#ocr-scheduler--resource-management) |\n| `includeRawContent` | `boolean` | `false` | Attach raw XML/RTF source to each node |\n| `serializeRawContent` | `boolean` | `true` | Re-serialize XML to clean strings (only if `includeRawContent: true`) |\n| `preserveXmlWhitespace` | `boolean` | `false` | Preserve original XML whitespace during serialization |\n| `includeBreakNodes` | `boolean` | `false` | Include typed break nodes: DOCX `w:br`/`w:cr`, ODF `fo:break-before`/`fo:break-after` and `text:soft-page-break` |\n| `ignoreInternalLinks` | `boolean` | `false` | Strip bookmarks and internal cross-references from AST (now honored for PDF too) |\n| `ignorePageGeometry` | `boolean` | `false` | Omit the geometric layout data: per-node bounding boxes (`node.bounds`) and page dimensions. Currently produced by the PDF parser |\n| `fileType` | `SupportedFileType \\| null` | `null` | **Required for text-based binary data** (`'md'`, `'html'`, `'csv'`) as these lack magic bytes. |\n| `csvDelimiter` | `string` | `','` | Input delimiter when parsing CSV files |\n| `decompressionLimits` | `DecompressionLimits` | `{ maxUncompressedBytes: 512MB, maxZipEntries: 10000, maxTableCells: 1000000 }` | **New**: Limits applied during ZIP extraction (and ODF cell expansion) to protect against excessive memory and resource usage |\n| `htmlParserConfig` | `HtmlParserConfig` | `{}` | HTML/XHTML/EPUB parsing options **(and Markdown input: `preserveIframes`/`embedFolkForms` govern raw `<iframe>` blocks and folk embeds in `.md` too)**. `preserveAttributes` (`boolean`, default `false`): keep generic source attributes no typed field consumed on `node.htmlAttributes`. `preserveIframes` (`boolean \\| string[]`, default `false`): preserve non-YouTube `<iframe>` embeds (otherwise dropped) as `embed` nodes: `true` for any, or a hostname allowlist; the src is scheme-checked on generation. `embedFolkForms` (`boolean`, default `false`): opt in to importing ambiguous folk embed forms (Obsidian `![](youtube-url)`, thumbnail-link) as YouTube embeds |\n| `pdfWorkerSrc` | `string` | CDN (jsDelivr) | Path/URL to `pdf.worker.min.mjs` (required in browser) |\n| `pdfParserConfig` | `PdfParserConfig` | see below | PDF-specific options ([table below](#pdfparserconfig)) |\n| `onWarning` | `(issue: OfficeIssue) => void` | — | Callback for non-fatal parsing issues |\n| `abortSignal` | `AbortSignal \\| null` | `null` | Optional signal to cancel parsing (rejects with AbortError) |\n\n---\n\n### PdfParserConfig\n\nPDF-specific options, passed as `pdfParserConfig` on the parser config.\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `useTags` | `boolean` | `true` | Use the tagged-structure tree (headings, tables, lists, notes) when present and reliable; set `false` to force geometry-only extraction |\n| `detectColumns` | `boolean` | `true` | Recover reading order for multi-column and float-beside-text pages (recursive XY-cut) |\n| `mergeHyphenatedWords` | `boolean` | `true` | Join words split across a line break by a trailing hyphen |\n| `lineToleranceFactor` | `number` | `0.35` | Baseline tolerance (fraction of font size) for grouping fragments onto one line |\n| `spaceToleranceFactor` | `number` | `0.25` | Gap threshold (fraction of font size) for inserting a space between fragments |\n| `headingDetection` | `'auto' \\| 'font-size' \\| 'off'` | `'auto'` | How heading levels are decided. `'auto'`: from tags when tagged, else a size/weight heuristic. `'font-size'`: re-level headings by the heuristic even on a tagged PDF (tables/lists stay tagged; a tagged heading is re-leveled by size and may be demoted). `'off'`: never emit headings |\n| `pageRange` | `string` | `''` (all) | Restrict to given pages, e.g. `'1-3,7'`. Output keeps original page numbers |\n| `normalizeText` | `boolean` | `true` | Unicode-normalize extracted text (expand ligatures, compose combining marks, regularize whitespace). Set `false` to preserve the raw source glyphs verbatim |\n| `extractTextColor` | `boolean` | `true` | Extract each run's fill color into `formatting.color`. Recovered from the operator list; on by default (color is content like bold/font). Costs about 1.6x parse time on a text-heavy PDF, near-free when `extractAttachments`/`ocr` already fetch the operator list; set `false` to skip it. Pure black is left unset. Highlight annotations set `formatting.backgroundColor` regardless of this flag |\n\n---\n\n### GeneratorConfig (Common)\n\nOptions shared by all generator formats. Pass to `OfficeGenerator.generate(ast, format, config)` or `ast.to(format, config)`.\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `includeFormatting` | `boolean` | `true` | Include bold/italic/colors/sizes in output (HTML, Markdown, DOCX, ODT, RTF; a no-op for text/CSV/chunks, which carry no run formatting) |\n| `generateIds` | `boolean` | `true` | Slug-based heading anchors: `id` attributes on HTML headings, and a `{#slug}` suffix on Markdown headings (`# Title {#title}`, kramdown/Pandoc). Set `false` to omit both, useful when the Markdown is rendered by GFM/CommonMark, which show `{#slug}` as literal text. A top-level option (not under `mdConfig`/`htmlConfig`); it affects HTML, Markdown, DOCX and ODT (the formats that carry a heading anchor/bookmark id). |\n| `renderMetadata` | `boolean` | `false` | Render title/author as a visible header block. Rendered by CSV, DOCX, HTML (and the Puppeteer PDF engine), EPUB, text, ODT and RTF; the native PDF engine and Markdown do not |\n| `metadataOverrides` | `MetadataOverrides` | `{}` | Override the metadata embedded in the output, merged per field over `ast.metadata` |\n| `includeImages` | `boolean \\| 'image-only' \\| 'image+ocr-text' \\| 'ocr-text-only' \\| 'none'` | `true` | How to render an image node. `true`=`'image-only'` (embed the image, no OCR text); `'image+ocr-text'` (image then its recognized/OCR text); `'ocr-text-only'` (OCR text, no image); `false`=`'none'` (omit). In plain-text output an image becomes an `[Image: name]` placeholder (plus OCR text for `'image+ocr-text'`), or just the OCR text for `'ocr-text-only'` |\n| `maxInlineImageBytes` | `number` | `1500000` | Max decoded image size, in bytes, that is inlined as a `data:` URI (HTML/Markdown); the base64 URI itself is ~1/3 larger, so a scanned page cannot emit a multi-megabyte line that breaks downstream parsers. Under the default `image-only` mode an image over the cap","readmeFilename":"README.md","users":{"w916797724":true}}