From 2f5dba12107d07d63c0a289eeebc075e37fd90e5 Mon Sep 17 00:00:00 2001 From: DiogenesBR Date: Fri, 22 Sep 2023 17:36:40 +0000 Subject: [PATCH] File loader --- poetry.lock | 274 +++++++++++++++++- pyproject.toml | 1 + .../components/documentloaders/FileLoader.py | 187 ++++++++++++ .../components/documentloaders/__init__.py | 0 4 files changed, 451 insertions(+), 11 deletions(-) create mode 100644 src/backend/langflow/components/documentloaders/FileLoader.py create mode 100644 src/backend/langflow/components/documentloaders/__init__.py diff --git a/poetry.lock b/poetry.lock index a3ae4895d..8c356b007 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.5.1 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand. [[package]] name = "aiofiles" @@ -737,6 +737,17 @@ files = [ {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, ] +[[package]] +name = "colorclass" +version = "2.2.2" +description = "Colorful worry-free console applications for Linux, Mac OS X, and Windows." +optional = false +python-versions = ">=2.6" +files = [ + {file = "colorclass-2.2.2-py2.py3-none-any.whl", hash = "sha256:6f10c273a0ef7a1150b1120b6095cbdd68e5cf36dfd5d0fc957a2500bbf99a55"}, + {file = "colorclass-2.2.2.tar.gz", hash = "sha256:6d4fe287766166a98ca7bc6f6312daf04a0481b1eda43e7173484051c0ab4366"}, +] + [[package]] name = "coloredlogs" version = "15.0.1" @@ -773,6 +784,16 @@ lint = ["black (>=22.6.0)", "mdformat (>0.7)", "mdformat-gfm (>=0.3.5)", "ruff ( test = ["pytest"] typing = ["mypy (>=0.990)"] +[[package]] +name = "compressed-rtf" +version = "1.0.6" +description = "Compressed Rich Text Format (RTF) compression and decompression package" +optional = false +python-versions = "*" +files = [ + {file = "compressed_rtf-1.0.6.tar.gz", hash = "sha256:c1c827f1d124d24608981a56e8b8691eb1f2a69a78ccad6440e7d92fde1781dd"}, +] + [[package]] name = "coverage" version = "7.3.1" @@ -1187,6 +1208,27 @@ files = [ {file = "duckdb-0.8.1.tar.gz", hash = "sha256:a54d37f4abc2afc4f92314aaa56ecf215a411f40af4bffe1e86bd25e62aceee9"}, ] +[[package]] +name = "easygui" +version = "0.98.3" +description = "EasyGUI is a module for very simple, very easy GUI programming in Python. EasyGUI is different from other GUI generators in that EasyGUI is NOT event-driven. Instead, all GUI interactions are invoked by simple function calls." +optional = false +python-versions = "*" +files = [ + {file = "easygui-0.98.3-py2.py3-none-any.whl", hash = "sha256:33498710c68b5376b459cd3fc48d1d1f33822139eb3ed01defbc0528326da3ba"}, + {file = "easygui-0.98.3.tar.gz", hash = "sha256:d653ff79ee1f42f63b5a090f2f98ce02335d86ad8963b3ce2661805cafe99a04"}, +] + +[[package]] +name = "ebcdic" +version = "1.1.1" +description = "Additional EBCDIC codecs" +optional = false +python-versions = "*" +files = [ + {file = "ebcdic-1.1.1-py2.py3-none-any.whl", hash = "sha256:33b4cb729bc2d0bf46cc1847b0e5946897cb8d3f53520c5b9aa5fa98d7e735f1"}, +] + [[package]] name = "ecdsa" version = "0.18.0" @@ -1247,6 +1289,32 @@ files = [ [package.extras] tests = ["asttokens", "littleutils", "pytest", "rich"] +[[package]] +name = "extract-msg" +version = "0.45.0" +description = "Extracts emails and attachments saved in Microsoft Outlook's .msg files" +optional = false +python-versions = ">=3.8" +files = [ + {file = "extract_msg-0.45.0-py2.py3-none-any.whl", hash = "sha256:af645ffe1534bce93b20390576dac2aee027c17a714365172d31b3894f810ca7"}, + {file = "extract_msg-0.45.0.tar.gz", hash = "sha256:6814865cf2ba806bd69af53af688a13e000a95d4991cce6a0416b3bdeb739496"}, +] + +[package.dependencies] +beautifulsoup4 = ">=4.11.1,<4.13" +compressed-rtf = ">=1.0.6,<2" +ebcdic = ">=1.1.1,<2" +imapclient = ">=2.3.0,<3" +olefile = "0.46" +red-black-tree-mod = "1.20" +RTFDE = ">=0.1.0,<0.2" +tzlocal = ">=4.2,<6" + +[package.extras] +all = ["extract-msg[image]", "extract-msg[mime]"] +image = ["Pillow (>=9.5.0,<10)"] +mime = ["python-magic (>=0.4.27,<0.5)"] + [[package]] name = "faiss-cpu" version = "1.7.4" @@ -1891,6 +1959,7 @@ files = [ {file = "greenlet-2.0.2-cp27-cp27m-win32.whl", hash = "sha256:6c3acb79b0bfd4fe733dff8bc62695283b57949ebcca05ae5c129eb606ff2d74"}, {file = "greenlet-2.0.2-cp27-cp27m-win_amd64.whl", hash = "sha256:283737e0da3f08bd637b5ad058507e578dd462db259f7f6e4c5c365ba4ee9343"}, {file = "greenlet-2.0.2-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:d27ec7509b9c18b6d73f2f5ede2622441de812e7b1a80bbd446cb0633bd3d5ae"}, + {file = "greenlet-2.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d967650d3f56af314b72df7089d96cda1083a7fc2da05b375d2bc48c82ab3f3c"}, {file = "greenlet-2.0.2-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:30bcf80dda7f15ac77ba5af2b961bdd9dbc77fd4ac6105cee85b0d0a5fcf74df"}, {file = "greenlet-2.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:26fbfce90728d82bc9e6c38ea4d038cba20b7faf8a0ca53a9c07b67318d46088"}, {file = "greenlet-2.0.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9190f09060ea4debddd24665d6804b995a9c122ef5917ab26e1566dcc712ceeb"}, @@ -1899,6 +1968,7 @@ files = [ {file = "greenlet-2.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:76ae285c8104046b3a7f06b42f29c7b73f77683df18c49ab5af7983994c2dd91"}, {file = "greenlet-2.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:2d4686f195e32d36b4d7cf2d166857dbd0ee9f3d20ae349b6bf8afc8485b3645"}, {file = "greenlet-2.0.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:c4302695ad8027363e96311df24ee28978162cdcdd2006476c43970b384a244c"}, + {file = "greenlet-2.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d4606a527e30548153be1a9f155f4e283d109ffba663a15856089fb55f933e47"}, {file = "greenlet-2.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c48f54ef8e05f04d6eff74b8233f6063cb1ed960243eacc474ee73a2ea8573ca"}, {file = "greenlet-2.0.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a1846f1b999e78e13837c93c778dcfc3365902cfb8d1bdb7dd73ead37059f0d0"}, {file = "greenlet-2.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a06ad5312349fec0ab944664b01d26f8d1f05009566339ac6f63f56589bc1a2"}, @@ -1928,6 +1998,7 @@ files = [ {file = "greenlet-2.0.2-cp37-cp37m-win32.whl", hash = "sha256:3f6ea9bd35eb450837a3d80e77b517ea5bc56b4647f5502cd28de13675ee12f7"}, {file = "greenlet-2.0.2-cp37-cp37m-win_amd64.whl", hash = "sha256:7492e2b7bd7c9b9916388d9df23fa49d9b88ac0640db0a5b4ecc2b653bf451e3"}, {file = "greenlet-2.0.2-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:b864ba53912b6c3ab6bcb2beb19f19edd01a6bfcbdfe1f37ddd1778abfe75a30"}, + {file = "greenlet-2.0.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1087300cf9700bbf455b1b97e24db18f2f77b55302a68272c56209d5587c12d1"}, {file = "greenlet-2.0.2-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:ba2956617f1c42598a308a84c6cf021a90ff3862eddafd20c3333d50f0edb45b"}, {file = "greenlet-2.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc3a569657468b6f3fb60587e48356fe512c1754ca05a564f11366ac9e306526"}, {file = "greenlet-2.0.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8eab883b3b2a38cc1e050819ef06a7e6344d4a990d24d45bc6f2cf959045a45b"}, @@ -1936,6 +2007,7 @@ files = [ {file = "greenlet-2.0.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b0ef99cdbe2b682b9ccbb964743a6aca37905fda5e0452e5ee239b1654d37f2a"}, {file = "greenlet-2.0.2-cp38-cp38-win32.whl", hash = "sha256:b80f600eddddce72320dbbc8e3784d16bd3fb7b517e82476d8da921f27d4b249"}, {file = "greenlet-2.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:4d2e11331fc0c02b6e84b0d28ece3a36e0548ee1a1ce9ddde03752d9b79bba40"}, + {file = "greenlet-2.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8512a0c38cfd4e66a858ddd1b17705587900dd760c6003998e9472b77b56d417"}, {file = "greenlet-2.0.2-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:88d9ab96491d38a5ab7c56dd7a3cc37d83336ecc564e4e8816dbed12e5aaefc8"}, {file = "greenlet-2.0.2-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:561091a7be172ab497a3527602d467e2b3fbe75f9e783d8b8ce403fa414f71a6"}, {file = "greenlet-2.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:971ce5e14dc5e73715755d0ca2975ac88cfdaefcaab078a284fea6cfabf866df"}, @@ -2381,6 +2453,24 @@ files = [ {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"}, ] +[[package]] +name = "imapclient" +version = "2.3.1" +description = "Easy-to-use, Pythonic and complete IMAP client library" +optional = false +python-versions = "*" +files = [ + {file = "IMAPClient-2.3.1-py2.py3-none-any.whl", hash = "sha256:057f28025d2987c63e065afb0e4370b0b850b539b0e1494cea0427e88130108c"}, + {file = "IMAPClient-2.3.1.zip", hash = "sha256:26ea995664fae3a88b878ebce2aff7402931697b86658b7882043ddb01b0e6ba"}, +] + +[package.dependencies] +six = "*" + +[package.extras] +doc = ["sphinx"] +test = ["mock (>=1.3.0)"] + [[package]] name = "importlib-metadata" version = "6.8.0" @@ -2936,6 +3026,22 @@ files = [ pydantic = ">=1,<3" requests = ">=2,<3" +[[package]] +name = "lark" +version = "1.1.5" +description = "a modern parsing library" +optional = false +python-versions = "*" +files = [ + {file = "lark-1.1.5-py3-none-any.whl", hash = "sha256:8476f9903e93fbde4f6c327f74d79e9b4bd0ed9294c5dfa3164ab8c581b5de2a"}, + {file = "lark-1.1.5.tar.gz", hash = "sha256:4b534eae1f9af5b4ea000bea95776350befe1981658eea3820a01c37e504bb4d"}, +] + +[package.extras] +atomic-cache = ["atomicwrites"] +nearley = ["js2py"] +regex = ["regex"] + [[package]] name = "linkify-it-py" version = "2.0.2" @@ -3002,10 +3108,13 @@ files = [ {file = "lxml-4.9.3-cp27-cp27m-macosx_11_0_x86_64.whl", hash = "sha256:b0a545b46b526d418eb91754565ba5b63b1c0b12f9bd2f808c852d9b4b2f9b5c"}, {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:075b731ddd9e7f68ad24c635374211376aa05a281673ede86cbe1d1b3455279d"}, {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:1e224d5755dba2f4a9498e150c43792392ac9b5380aa1b845f98a1618c94eeef"}, + {file = "lxml-4.9.3-cp27-cp27m-win32.whl", hash = "sha256:2c74524e179f2ad6d2a4f7caf70e2d96639c0954c943ad601a9e146c76408ed7"}, + {file = "lxml-4.9.3-cp27-cp27m-win_amd64.whl", hash = "sha256:4f1026bc732b6a7f96369f7bfe1a4f2290fb34dce00d8644bc3036fb351a4ca1"}, {file = "lxml-4.9.3-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c0781a98ff5e6586926293e59480b64ddd46282953203c76ae15dbbbf302e8bb"}, {file = "lxml-4.9.3-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:cef2502e7e8a96fe5ad686d60b49e1ab03e438bd9123987994528febd569868e"}, {file = "lxml-4.9.3-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:b86164d2cff4d3aaa1f04a14685cbc072efd0b4f99ca5708b2ad1b9b5988a991"}, {file = "lxml-4.9.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:42871176e7896d5d45138f6d28751053c711ed4d48d8e30b498da155af39aebd"}, + {file = "lxml-4.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:ae8b9c6deb1e634ba4f1930eb67ef6e6bf6a44b6eb5ad605642b2d6d5ed9ce3c"}, {file = "lxml-4.9.3-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:411007c0d88188d9f621b11d252cce90c4a2d1a49db6c068e3c16422f306eab8"}, {file = "lxml-4.9.3-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:cd47b4a0d41d2afa3e58e5bf1f62069255aa2fd6ff5ee41604418ca925911d76"}, {file = "lxml-4.9.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0e2cb47860da1f7e9a5256254b74ae331687b9672dfa780eed355c4c9c3dbd23"}, @@ -3014,6 +3123,7 @@ files = [ {file = "lxml-4.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:97047f0d25cd4bcae81f9ec9dc290ca3e15927c192df17331b53bebe0e3ff96d"}, {file = "lxml-4.9.3-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:1f447ea5429b54f9582d4b955f5f1985f278ce5cf169f72eea8afd9502973dd5"}, {file = "lxml-4.9.3-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:57d6ba0ca2b0c462f339640d22882acc711de224d769edf29962b09f77129cbf"}, + {file = "lxml-4.9.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:9767e79108424fb6c3edf8f81e6730666a50feb01a328f4a016464a5893f835a"}, {file = "lxml-4.9.3-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:71c52db65e4b56b8ddc5bb89fb2e66c558ed9d1a74a45ceb7dcb20c191c3df2f"}, {file = "lxml-4.9.3-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:d73d8ecf8ecf10a3bd007f2192725a34bd62898e8da27eb9d32a58084f93962b"}, {file = "lxml-4.9.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0a3d3487f07c1d7f150894c238299934a2a074ef590b583103a45002035be120"}, @@ -3033,6 +3143,7 @@ files = [ {file = "lxml-4.9.3-cp36-cp36m-macosx_11_0_x86_64.whl", hash = "sha256:64f479d719dc9f4c813ad9bb6b28f8390360660b73b2e4beb4cb0ae7104f1c12"}, {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:dd708cf4ee4408cf46a48b108fb9427bfa00b9b85812a9262b5c668af2533ea5"}, {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c31c7462abdf8f2ac0577d9f05279727e698f97ecbb02f17939ea99ae8daa98"}, + {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:e3cd95e10c2610c360154afdc2f1480aea394f4a4f1ea0a5eacce49640c9b190"}, {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:4930be26af26ac545c3dffb662521d4e6268352866956672231887d18f0eaab2"}, {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4aec80cde9197340bc353d2768e2a75f5f60bacda2bab72ab1dc499589b3878c"}, {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:14e019fd83b831b2e61baed40cab76222139926b1fb5ed0e79225bc0cae14584"}, @@ -3042,6 +3153,7 @@ files = [ {file = "lxml-4.9.3-cp36-cp36m-win_amd64.whl", hash = "sha256:bef4e656f7d98aaa3486d2627e7d2df1157d7e88e7efd43a65aa5dd4714916cf"}, {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:46f409a2d60f634fe550f7133ed30ad5321ae2e6630f13657fb9479506b00601"}, {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:4c28a9144688aef80d6ea666c809b4b0e50010a2aca784c97f5e6bf143d9f129"}, + {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:141f1d1a9b663c679dc524af3ea1773e618907e96075262726c7612c02b149a4"}, {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:53ace1c1fd5a74ef662f844a0413446c0629d151055340e9893da958a374f70d"}, {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:17a753023436a18e27dd7769e798ce302963c236bc4114ceee5b25c18c52c693"}, {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:7d298a1bd60c067ea75d9f684f5f3992c9d6766fadbc0bcedd39750bf344c2f4"}, @@ -3051,6 +3163,7 @@ files = [ {file = "lxml-4.9.3-cp37-cp37m-win_amd64.whl", hash = "sha256:120fa9349a24c7043854c53cae8cec227e1f79195a7493e09e0c12e29f918e52"}, {file = "lxml-4.9.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:4d2d1edbca80b510443f51afd8496be95529db04a509bc8faee49c7b0fb6d2cc"}, {file = "lxml-4.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:8d7e43bd40f65f7d97ad8ef5c9b1778943d02f04febef12def25f7583d19baac"}, + {file = "lxml-4.9.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:71d66ee82e7417828af6ecd7db817913cb0cf9d4e61aa0ac1fde0583d84358db"}, {file = "lxml-4.9.3-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:6fc3c450eaa0b56f815c7b62f2b7fba7266c4779adcf1cece9e6deb1de7305ce"}, {file = "lxml-4.9.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:65299ea57d82fb91c7f019300d24050c4ddeb7c5a190e076b5f48a2b43d19c42"}, {file = "lxml-4.9.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:eadfbbbfb41b44034a4c757fd5d70baccd43296fb894dba0295606a7cf3124aa"}, @@ -3060,6 +3173,7 @@ files = [ {file = "lxml-4.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:92af161ecbdb2883c4593d5ed4815ea71b31fafd7fd05789b23100d081ecac96"}, {file = "lxml-4.9.3-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:9bb6ad405121241e99a86efff22d3ef469024ce22875a7ae045896ad23ba2340"}, {file = "lxml-4.9.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:8ed74706b26ad100433da4b9d807eae371efaa266ffc3e9191ea436087a9d6a7"}, + {file = "lxml-4.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:fbf521479bcac1e25a663df882c46a641a9bff6b56dc8b0fafaebd2f66fb231b"}, {file = "lxml-4.9.3-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:303bf1edce6ced16bf67a18a1cf8339d0db79577eec5d9a6d4a80f0fb10aa2da"}, {file = "lxml-4.9.3-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:5515edd2a6d1a5a70bfcdee23b42ec33425e405c5b351478ab7dc9347228f96e"}, {file = "lxml-4.9.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:690dafd0b187ed38583a648076865d8c229661ed20e48f2335d68e2cf7dc829d"}, @@ -3070,13 +3184,16 @@ files = [ {file = "lxml-4.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:4dd9a263e845a72eacb60d12401e37c616438ea2e5442885f65082c276dfb2b2"}, {file = "lxml-4.9.3-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6689a3d7fd13dc687e9102a27e98ef33730ac4fe37795d5036d18b4d527abd35"}, {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:f6bdac493b949141b733c5345b6ba8f87a226029cbabc7e9e121a413e49441e0"}, + {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:05186a0f1346ae12553d66df1cfce6f251589fea3ad3da4f3ef4e34b2d58c6a3"}, {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c2006f5c8d28dee289f7020f721354362fa304acbaaf9745751ac4006650254b"}, {file = "lxml-4.9.3-pp38-pypy38_pp73-macosx_11_0_x86_64.whl", hash = "sha256:5c245b783db29c4e4fbbbfc9c5a78be496c9fea25517f90606aa1f6b2b3d5f7b"}, {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:4fb960a632a49f2f089d522f70496640fdf1218f1243889da3822e0a9f5f3ba7"}, + {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:50670615eaf97227d5dc60de2dc99fb134a7130d310d783314e7724bf163f75d"}, {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:9719fe17307a9e814580af1f5c6e05ca593b12fb7e44fe62450a5384dbf61b4b"}, {file = "lxml-4.9.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:3331bece23c9ee066e0fb3f96c61322b9e0f54d775fccefff4c38ca488de283a"}, {file = "lxml-4.9.3-pp39-pypy39_pp73-macosx_11_0_x86_64.whl", hash = "sha256:ed667f49b11360951e201453fc3967344d0d0263aa415e1619e85ae7fd17b4e0"}, {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:8b77946fd508cbf0fccd8e400a7f71d4ac0e1595812e66025bac475a8e811694"}, + {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:e4da8ca0c0c0aea88fd46be8e44bd49716772358d648cce45fe387f7b92374a7"}, {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:fe4bda6bd4340caa6e5cf95e73f8fea5c4bfc55763dd42f1b50a94c1b4a2fbd4"}, {file = "lxml-4.9.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:f3df3db1d336b9356dd3112eae5f5c2b8b377f3bc826848567f10bfddfee77e9"}, {file = "lxml-4.9.3.tar.gz", hash = "sha256:48628bd53a426c9eb9bc066a923acaa0878d1e86129fd5359aee99285f4eed9c"}, @@ -3190,6 +3307,16 @@ files = [ {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"}, {file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"}, {file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f698de3fd0c4e6972b92290a45bd9b1536bffe8c6759c62471efaa8acb4c37bc"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aa57bd9cf8ae831a362185ee444e15a93ecb2e344c8e52e4d721ea3ab6ef1823"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffcc3f7c66b5f5b7931a5aa68fc9cecc51e685ef90282f4a82f0f5e9b704ad11"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47d4f1c5f80fc62fdd7777d0d40a2e9dda0a05883ab11374334f6c4de38adffd"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1f67c7038d560d92149c060157d623c542173016c4babc0c1913cca0564b9939"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9aad3c1755095ce347e26488214ef77e0485a3c34a50c5a5e2471dff60b9dd9c"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:14ff806850827afd6b07a5f32bd917fb7f45b046ba40c57abdb636674a8b559c"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8f9293864fe09b8149f0cc42ce56e3f0e54de883a9de90cd427f191c346eb2e1"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-win32.whl", hash = "sha256:715d3562f79d540f251b99ebd6d8baa547118974341db04f5ad06d5ea3eb8007"}, + {file = "MarkupSafe-2.1.3-cp312-cp312-win_amd64.whl", hash = "sha256:1b8dd8c3fd14349433c79fa8abeb573a55fc0fdd769133baac1f5e07abf54aeb"}, {file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"}, {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"}, {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"}, @@ -3354,6 +3481,21 @@ docs = ["sphinx"] gmpy = ["gmpy2 (>=2.1.0a4)"] tests = ["pytest (>=4.6)"] +[[package]] +name = "msoffcrypto-tool" +version = "5.1.1" +description = "Python tool and library for decrypting MS Office files with passwords or other keys" +optional = false +python-versions = ">=3.8,<4.0" +files = [ + {file = "msoffcrypto_tool-5.1.1-py3-none-any.whl", hash = "sha256:27475aaf8a70485471ad86426c0be10ee4e24c6fad70335e4a8f88d2da323ca1"}, + {file = "msoffcrypto_tool-5.1.1.tar.gz", hash = "sha256:5585a303fa3ee49eec0253f912be17b82cf83f13f0f7489b4ea10f4ecb285278"}, +] + +[package.dependencies] +cryptography = ">=35.0" +olefile = ">=0.46" + [[package]] name = "multidict" version = "6.0.4" @@ -3684,6 +3826,38 @@ files = [ {file = "numpy-1.26.0.tar.gz", hash = "sha256:f93fc78fe8bf15afe2b8d6b6499f1c73953169fad1e9a8dd086cdff3190e7fdf"}, ] +[[package]] +name = "olefile" +version = "0.46" +description = "Python package to parse, read and write Microsoft OLE2 files (Structured Storage or Compound Document, Microsoft Office)" +optional = false +python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*" +files = [ + {file = "olefile-0.46.zip", hash = "sha256:133b031eaf8fd2c9399b78b8bc5b8fcbe4c31e85295749bb17a87cba8f3c3964"}, +] + +[[package]] +name = "oletools" +version = "0.60.1" +description = "Python tools to analyze security characteristics of MS Office and OLE files (also called Structured Storage, Compound File Binary Format or Compound Document File Format), for Malware Analysis and Incident Response #DFIR" +optional = false +python-versions = "*" +files = [ + {file = "oletools-0.60.1-py2.py3-none-any.whl", hash = "sha256:edef92374e688989a39269eb9a11142fb20a023629c23538c849c14d1d1144ea"}, + {file = "oletools-0.60.1.zip", hash = "sha256:67a796da4c4b8e2feb9a6b2495bef8798a3323a75512de4e5669d9dc9d1fae31"}, +] + +[package.dependencies] +colorclass = "*" +easygui = "*" +msoffcrypto-tool = {version = "*", markers = "platform_python_implementation != \"PyPy\" or python_version >= \"3\" and (platform_system != \"Windows\" and platform_system != \"Darwin\")"} +olefile = ">=0.46" +pcodedmp = ">=1.2.5" +pyparsing = ">=2.1.0,<3" + +[package.extras] +full = ["XLMMacroDeobfuscator"] + [[package]] name = "onnxruntime" version = "1.15.1" @@ -4212,6 +4386,21 @@ files = [ {file = "pathspec-0.11.2.tar.gz", hash = "sha256:e0d8d0ac2f12da61956eb2306b69f9469b42f4deb0f3cb6ed47b9cce9996ced3"}, ] +[[package]] +name = "pcodedmp" +version = "1.2.6" +description = "A VBA p-code disassembler" +optional = false +python-versions = "*" +files = [ + {file = "pcodedmp-1.2.6-py2.py3-none-any.whl", hash = "sha256:4441f7c0ab4cbda27bd4668db3b14f36261d86e5059ce06c0828602cbe1c4278"}, + {file = "pcodedmp-1.2.6.tar.gz", hash = "sha256:025f8c809a126f45a082ffa820893e6a8d990d9d7ddb68694b5a9f0a6dbcd955"}, +] + +[package.dependencies] +oletools = ">=0.54" +win-unicode-console = {version = "*", markers = "platform_system == \"Windows\" and platform_python_implementation != \"PyPy\""} + [[package]] name = "pexpect" version = "4.8.0" @@ -5014,18 +5203,15 @@ zstd = ["zstandard"] [[package]] name = "pyparsing" -version = "3.1.1" -description = "pyparsing module - Classes and methods to define and execute parsing grammars" +version = "2.4.7" +description = "Python parsing module" optional = false -python-versions = ">=3.6.8" +python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*" files = [ - {file = "pyparsing-3.1.1-py3-none-any.whl", hash = "sha256:32c7c0b711493c72ff18a981d24f28aaf9c1fb7ed5e9667c9e84e3db623bdbfb"}, - {file = "pyparsing-3.1.1.tar.gz", hash = "sha256:ede28a1a32462f5a9705e07aea48001a08f7cf81a021585011deba701581a0db"}, + {file = "pyparsing-2.4.7-py2.py3-none-any.whl", hash = "sha256:ef9d7589ef3c200abe66653d3f1ab1033c3c419ae9b9bdb1240a85b024efc88b"}, + {file = "pyparsing-2.4.7.tar.gz", hash = "sha256:c203ec8783bf771a155b207279b9bccb8dea02d8f0c9e5f8ead507bc3246ecc1"}, ] -[package.extras] -diagrams = ["jinja2", "railroad-diagrams"] - [[package]] name = "pypdf" version = "3.16.1" @@ -5292,6 +5478,7 @@ files = [ {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"}, + {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"}, {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"}, {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"}, {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"}, @@ -5299,8 +5486,15 @@ files = [ {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"}, + {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"}, {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"}, {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, + {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"}, + {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"}, + {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"}, + {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"}, + {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"}, + {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"}, {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"}, @@ -5317,6 +5511,7 @@ files = [ {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"}, + {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"}, {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"}, {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"}, {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"}, @@ -5324,6 +5519,7 @@ files = [ {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"}, + {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"}, {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"}, {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"}, {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"}, @@ -5492,6 +5688,16 @@ python-dateutil = ">=2.8.1,<3.0.0" typing-extensions = ">=4.2.0,<5.0.0" websockets = ">=10.3,<11.0" +[[package]] +name = "red-black-tree-mod" +version = "1.20" +description = "Flexible python implementation of red black trees" +optional = false +python-versions = "*" +files = [ + {file = "red-black-tree-mod-1.20.tar.gz", hash = "sha256:2448e6fc9cbf1be204c753f352c6ee49aa8156dbf1faa57dfc26bd7705077e0a"}, +] + [[package]] name = "regex" version = "2023.8.8" @@ -5673,6 +5879,25 @@ files = [ [package.dependencies] pyasn1 = ">=0.1.3" +[[package]] +name = "rtfde" +version = "0.1.0" +description = "A library for extracting HTML content from RTF encapsulated HTML as commonly found in the exchange MSG email format." +optional = false +python-versions = ">=3.6" +files = [ + {file = "RTFDE-0.1.0-py3-none-any.whl", hash = "sha256:a110dbef435803f3fba717d51a7b9c7a92695c2461637cc6eaf36a9f54386e26"}, + {file = "RTFDE-0.1.0.tar.gz", hash = "sha256:12215ee59856208010b9200c19afe0f9fa13a3fb39f44015979299c248cbacd7"}, +] + +[package.dependencies] +lark = "1.1.5" +oletools = ">=0.56" + +[package.extras] +dev = ["coverage (>=7.2.2)", "lxml (>=4.6)", "mypy (>=1.1.1)", "pdoc3 (>=0.10.0)"] +msg-parse = ["extract-msg (>=0.27)"] + [[package]] name = "ruff" version = "0.0.254" @@ -6105,7 +6330,7 @@ files = [ ] [package.dependencies] -greenlet = {version = "!=0.4.17", markers = "python_version >= \"3\" and (platform_machine == \"win32\" or platform_machine == \"WIN32\" or platform_machine == \"AMD64\" or platform_machine == \"amd64\" or platform_machine == \"x86_64\" or platform_machine == \"ppc64le\" or platform_machine == \"aarch64\")"} +greenlet = {version = "!=0.4.17", markers = "python_version >= \"3\" and (platform_machine == \"aarch64\" or platform_machine == \"ppc64le\" or platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"AMD64\" or platform_machine == \"win32\" or platform_machine == \"WIN32\")"} [package.extras] aiomysql = ["aiomysql", "greenlet (!=0.4.17)"] @@ -6890,6 +7115,23 @@ files = [ {file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"}, ] +[[package]] +name = "tzlocal" +version = "5.0.1" +description = "tzinfo object for the local timezone" +optional = false +python-versions = ">=3.7" +files = [ + {file = "tzlocal-5.0.1-py3-none-any.whl", hash = "sha256:f3596e180296aaf2dbd97d124fe76ae3a0e3d32b258447de7b939b3fd4be992f"}, + {file = "tzlocal-5.0.1.tar.gz", hash = "sha256:46eb99ad4bdb71f3f72b7d24f4267753e240944ecfc16f25d2719ba89827a803"}, +] + +[package.dependencies] +tzdata = {version = "*", markers = "platform_system == \"Windows\""} + +[package.extras] +devenv = ["black", "check-manifest", "flake8", "pyroma", "pytest (>=4.3)", "pytest-cov", "pytest-mock (>=3.3)", "zest.releaser"] + [[package]] name = "uc-micro-py" version = "1.0.2" @@ -7276,6 +7518,16 @@ files = [ beautifulsoup4 = "*" requests = ">=2.0.0,<3.0.0" +[[package]] +name = "win-unicode-console" +version = "0.5" +description = "Enable Unicode input and display when running Python from Windows console." +optional = false +python-versions = "*" +files = [ + {file = "win_unicode_console-0.5.zip", hash = "sha256:d4142d4d56d46f449d6f00536a73625a871cba040f0bc1a2e305a04578f07d1e"}, +] + [[package]] name = "win32-setctime" version = "1.1.0" @@ -7542,4 +7794,4 @@ local = ["ctransformers", "llama-cpp-python", "sentence-transformers"] [metadata] lock-version = "2.0" python-versions = ">=3.9,<3.11" -content-hash = "628b8e0e42db9545e94410ef0c4e33edb1fe93c34d1b41b27ba7950a04b9df6c" +content-hash = "cb2ecbcb4831a845c7838b947312e812c8d10719351e2999dbeeddf44460f552" diff --git a/pyproject.toml b/pyproject.toml index 5429c0293..68b3b289a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -83,6 +83,7 @@ langfuse = "^1.0.13" pillow = "^10.0.0" metal-sdk = "^2.0.2" markupsafe = "^2.1.3" +extract-msg = "^0.45.0" [tool.poetry.group.dev.dependencies] black = "^23.1.0" diff --git a/src/backend/langflow/components/documentloaders/FileLoader.py b/src/backend/langflow/components/documentloaders/FileLoader.py new file mode 100644 index 000000000..3dbffe784 --- /dev/null +++ b/src/backend/langflow/components/documentloaders/FileLoader.py @@ -0,0 +1,187 @@ +from langflow import CustomComponent +from langchain.schema import Document + + +class FileLoaderComponent(CustomComponent): + display_name: str = "File Loader Component" + description: str = "Generic File Loader" + + loaders_info = [ + { + "loader": "AirbyteJSONLoader", + "name": "Airbyte JSON (.jsonl)", + "import": "langchain.document_loaders.AirbyteJSONLoader", + "defaultFor": ["jsonl"], + "allowdTypes": ["jsonl"], + }, + { + "loader": "BSHTMLLoader", + "name": "BeautifulSoup4 HTML (.html, .htm)", + "import": "langchain.document_loaders.BSHTMLLoader", + "allowdTypes": ["html", "htm"], + }, + { + "loader": "CSVLoader", + "name": "CSV (.csv)", + "import": "langchain.document_loaders.CSVLoader", + "defaultFor": ["csv"], + "allowdTypes": ["csv"], + }, + { + "loader": "CoNLLULoader", + "name": "CoNLL-U (.conllu)", + "import": "langchain.document_loaders.CoNLLULoader", + "defaultFor": ["conllu"], + "allowdTypes": ["conllu"], + }, + { + "loader": "EverNoteLoader", + "name": "EverNote (.enex)", + "import": "langchain.document_loaders.EverNoteLoader", + "defaultFor": ["enex"], + "allowdTypes": ["enex"], + }, + { + "loader": "FacebookChatLoader", + "name": "Facebook Chat (.json)", + "import": "langchain.document_loaders.FacebookChatLoader", + "allowdTypes": ["json"], + }, + { + "loader": "OutlookMessageLoader", + "name": "Outlook Message (.msg)", + "import": "langchain.document_loaders.OutlookMessageLoader", + "defaultFor": ["msg"], + "allowdTypes": ["msg"], + }, + { + "loader": "PyPDFLoader", + "name": "PyPDF (.pdf)", + "import": "langchain.document_loaders.PyPDFLoader", + "defaultFor": ["pdf"], + "allowdTypes": ["pdf"], + }, + { + "loader": "STRLoader", + "name": "Subtitle (.str)", + "import": "langchain.document_loaders.STRLoader", + "defaultFor": ["str"], + "allowdTypes": ["str"], + }, + { + "loader": "TextLoader", + "name": "Text (.txt)", + "import": "langchain.document_loaders.TextLoader", + "defaultFor": ["txt"], + "allowdTypes": ["txt"], + }, + { + "loader": "UnstructuredEmailLoader", + "name": "Unstructured Email (.eml)", + "import": "langchain.document_loaders.UnstructuredEmailLoader", + "defaultFor": ["eml"], + "allowdTypes": ["eml"], + }, + { + "loader": "UnstructuredHTMLLoader", + "name": "Unstructured HTML (.html, .htm)", + "import": "langchain.document_loaders.UnstructuredHTMLLoader", + "defaultFor": ["html", "htm"], + "allowdTypes": ["html", "htm"], + }, + { + "loader": "UnstructuredMarkdownLoader", + "name": "Unstructured Markdown (.md)", + "import": "langchain.document_loaders.UnstructuredMarkdownLoader", + "defaultFor": ["md"], + "allowdTypes": ["md"], + }, + { + "loader": "UnstructuredPowerPointLoader", + "name": "Unstructured PowerPoint (.pptx)", + "import": "langchain.document_loaders.UnstructuredPowerPointLoader", + "defaultFor": ["pptx"], + "allowdTypes": ["pptx"], + }, + { + "loader": "UnstructuredWordLoader", + "name": "Unstructured Word (.docx)", + "import": "langchain.document_loaders.UnstructuredWordLoader", + "defaultFor": ["docx"], + "allowdTypes": ["docx"], + }, + ] + + def build_config(self): + loader_options = ["Automatic"] + [ + loader_info["name"] for loader_info in self.loaders_info + ] + + file_types = [] + suffixes = [] + + for loader_info in self.loaders_info: + if "allowedTypes" in loader_info: + file_types.extend(loader_info["allowedTypes"]) + suffixes.extend([f".{ext}" for ext in loader_info["allowedTypes"]]) + + return { + "file_path": { + "display_name": "File Path", + "required": True, + "field_type": "file", + "file_types": ["*"], + "suffixes": ["*"], + # "file_types": file_types, + # "suffixes": suffixes, + }, + "loader": { + "display_name": "Loader", + "is_list": True, + "required": True, + "options": loader_options, + "value": "Automatic", + }, + "code": {"show": False}, + } + + def build(self, file_path: str, loader: str) -> Document: + file_type = file_path.split(".")[-1] + + # Mapeie o nome do loader selecionado para suas informações + selected_loader_info = None + for loader_info in self.loaders_info: + if loader_info["name"] == loader: + selected_loader_info = loader_info + break + + if selected_loader_info is None and loader != "Automatic": + raise ValueError(f"Loader {loader} not found in the loader info list") + + if loader == "Automatic": + # Determine o loader automaticamente com base na extensão do arquivo + default_loader_info = None + for info in self.loaders_info: + if "defaultFor" in info and file_type in info["defaultFor"]: + default_loader_info = info + break + + if default_loader_info is None: + raise ValueError(f"No default loader found for file type: {file_type}") + + selected_loader_info = default_loader_info + + loader_import = selected_loader_info["import"] + module_name, class_name = loader_import.rsplit(".", 1) + + try: + # Importe o loader dinamicamente + loader_module = __import__(module_name, fromlist=[class_name]) + loader_instance = getattr(loader_module, class_name) + except ImportError as e: + raise ValueError( + f"Loader {loader} could not be imported\nLoader info:\n{selected_loader_info}" + ) from e + + result = loader_instance(file_path=file_path) + return result.load() diff --git a/src/backend/langflow/components/documentloaders/__init__.py b/src/backend/langflow/components/documentloaders/__init__.py new file mode 100644 index 000000000..e69de29bb