feat(baoyu-translate): add three-mode translation skill with glossary support

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Jim Liu 宝玉
2026-03-05 19:32:27 -06:00
parent ce259e4547
commit 5b4ba3ac3f
13 changed files with 1119 additions and 3 deletions
+161
View File
@@ -0,0 +1,161 @@
{
"lockfileVersion": 1,
"workspaces": {
"": {
"dependencies": {
"remark-frontmatter": "^5.0.0",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"remark-stringify": "^11.0.0",
"unified": "^11.0.5",
},
},
},
"packages": {
"@types/debug": ["@types/debug@4.1.12", "", { "dependencies": { "@types/ms": "*" } }, "sha512-vIChWdVG3LG1SMxEvI/AK+FWJthlrqlTu7fbrlywTkkaONwk/UAGaULXRlf8vkzFBLVm0zkMdCquhL5aOjhXPQ=="],
"@types/mdast": ["@types/mdast@4.0.4", "", { "dependencies": { "@types/unist": "*" } }, "sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA=="],
"@types/ms": ["@types/ms@2.1.0", "", {}, "sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA=="],
"@types/unist": ["@types/unist@3.0.3", "", {}, "sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q=="],
"bail": ["bail@2.0.2", "", {}, "sha512-0xO6mYd7JB2YesxDKplafRpsiOzPt9V02ddPCLbY1xYGPOX24NTyN50qnUxgCPcSoYMhKpAuBTjQoRZCAkUDRw=="],
"ccount": ["ccount@2.0.1", "", {}, "sha512-eyrF0jiFpY+3drT6383f1qhkbGsLSifNAjA61IUjZjmLCWjItY6LB9ft9YhoDgwfmclB2zhu51Lc7+95b8NRAg=="],
"character-entities": ["character-entities@2.0.2", "", {}, "sha512-shx7oQ0Awen/BRIdkjkvz54PnEEI/EjwXDSIZp86/KKdbafHh1Df/RYGBhn4hbe2+uKC9FnT5UCEdyPz3ai9hQ=="],
"debug": ["debug@4.4.3", "", { "dependencies": { "ms": "^2.1.3" } }, "sha512-RGwwWnwQvkVfavKVt22FGLw+xYSdzARwm0ru6DhTVA3umU5hZc28V3kO4stgYryrTlLpuvgI9GiijltAjNbcqA=="],
"decode-named-character-reference": ["decode-named-character-reference@1.3.0", "", { "dependencies": { "character-entities": "^2.0.0" } }, "sha512-GtpQYB283KrPp6nRw50q3U9/VfOutZOe103qlN7BPP6Ad27xYnOIWv4lPzo8HCAL+mMZofJ9KEy30fq6MfaK6Q=="],
"dequal": ["dequal@2.0.3", "", {}, "sha512-0je+qPKHEMohvfRTCEo3CrPG6cAzAYgmzKyxRiYSSDkS6eGJdyVJm7WaYA5ECaAD9wLB2T4EEeymA5aFVcYXCA=="],
"devlop": ["devlop@1.1.0", "", { "dependencies": { "dequal": "^2.0.0" } }, "sha512-RWmIqhcFf1lRYBvNmr7qTNuyCt/7/ns2jbpp1+PalgE/rDQcBT0fioSMUpJ93irlUhC5hrg4cYqe6U+0ImW0rA=="],
"escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="],
"extend": ["extend@3.0.2", "", {}, "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g=="],
"fault": ["fault@2.0.1", "", { "dependencies": { "format": "^0.2.0" } }, "sha512-WtySTkS4OKev5JtpHXnib4Gxiurzh5NCGvWrFaZ34m6JehfTUhKZvn9njTfw48t6JumVQOmrKqpmGcdwxnhqBQ=="],
"format": ["format@0.2.2", "", {}, "sha512-wzsgA6WOq+09wrU1tsJ09udeR/YZRaeArL9e1wPbFg3GG2yDnC2ldKpxs4xunpFF9DgqCqOIra3bc1HWrJ37Ww=="],
"is-plain-obj": ["is-plain-obj@4.1.0", "", {}, "sha512-+Pgi+vMuUNkJyExiMBt5IlFoMyKnr5zhJ4Uspz58WOhBF5QoIZkFyNHIbBAtHwzVAgk5RtndVNsDRN61/mmDqg=="],
"longest-streak": ["longest-streak@3.1.0", "", {}, "sha512-9Ri+o0JYgehTaVBBDoMqIl8GXtbWg711O3srftcHhZ0dqnETqLaoIK0x17fUw9rFSlK/0NlsKe0Ahhyl5pXE2g=="],
"markdown-table": ["markdown-table@3.0.4", "", {}, "sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw=="],
"mdast-util-find-and-replace": ["mdast-util-find-and-replace@3.0.2", "", { "dependencies": { "@types/mdast": "^4.0.0", "escape-string-regexp": "^5.0.0", "unist-util-is": "^6.0.0", "unist-util-visit-parents": "^6.0.0" } }, "sha512-Tmd1Vg/m3Xz43afeNxDIhWRtFZgM2VLyaf4vSTYwudTyeuTneoL3qtWMA5jeLyz/O1vDJmmV4QuScFCA2tBPwg=="],
"mdast-util-from-markdown": ["mdast-util-from-markdown@2.0.3", "", { "dependencies": { "@types/mdast": "^4.0.0", "@types/unist": "^3.0.0", "decode-named-character-reference": "^1.0.0", "devlop": "^1.0.0", "mdast-util-to-string": "^4.0.0", "micromark": "^4.0.0", "micromark-util-decode-numeric-character-reference": "^2.0.0", "micromark-util-decode-string": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0", "unist-util-stringify-position": "^4.0.0" } }, "sha512-W4mAWTvSlKvf8L6J+VN9yLSqQ9AOAAvHuoDAmPkz4dHf553m5gVj2ejadHJhoJmcmxEnOv6Pa8XJhpxE93kb8Q=="],
"mdast-util-frontmatter": ["mdast-util-frontmatter@2.0.1", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.0.0", "escape-string-regexp": "^5.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0", "micromark-extension-frontmatter": "^2.0.0" } }, "sha512-LRqI9+wdgC25P0URIJY9vwocIzCcksduHQ9OF2joxQoyTNVduwLAFUzjoopuRJbJAReaKrNQKAZKL3uCMugWJA=="],
"mdast-util-gfm": ["mdast-util-gfm@3.1.0", "", { "dependencies": { "mdast-util-from-markdown": "^2.0.0", "mdast-util-gfm-autolink-literal": "^2.0.0", "mdast-util-gfm-footnote": "^2.0.0", "mdast-util-gfm-strikethrough": "^2.0.0", "mdast-util-gfm-table": "^2.0.0", "mdast-util-gfm-task-list-item": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-0ulfdQOM3ysHhCJ1p06l0b0VKlhU0wuQs3thxZQagjcjPrlFRqY215uZGHHJan9GEAXd9MbfPjFJz+qMkVR6zQ=="],
"mdast-util-gfm-autolink-literal": ["mdast-util-gfm-autolink-literal@2.0.1", "", { "dependencies": { "@types/mdast": "^4.0.0", "ccount": "^2.0.0", "devlop": "^1.0.0", "mdast-util-find-and-replace": "^3.0.0", "micromark-util-character": "^2.0.0" } }, "sha512-5HVP2MKaP6L+G6YaxPNjuL0BPrq9orG3TsrZ9YXbA3vDw/ACI4MEsnoDpn6ZNm7GnZgtAcONJyPhOP8tNJQavQ=="],
"mdast-util-gfm-footnote": ["mdast-util-gfm-footnote@2.1.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.1.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0" } }, "sha512-sqpDWlsHn7Ac9GNZQMeUzPQSMzR6Wv0WKRNvQRg0KqHh02fpTz69Qc1QSseNX29bhz1ROIyNyxExfawVKTm1GQ=="],
"mdast-util-gfm-strikethrough": ["mdast-util-gfm-strikethrough@2.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-mKKb915TF+OC5ptj5bJ7WFRPdYtuHv0yTRxK2tJvi+BDqbkiG7h7u/9SI89nRAYcmap2xHQL9D+QG/6wSrTtXg=="],
"mdast-util-gfm-table": ["mdast-util-gfm-table@2.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.0.0", "markdown-table": "^3.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-78UEvebzz/rJIxLvE7ZtDd/vIQ0RHv+3Mh5DR96p7cS7HsBhYIICDBCu8csTNWNO6tBWfqXPWekRuj2FNOGOZg=="],
"mdast-util-gfm-task-list-item": ["mdast-util-gfm-task-list-item@2.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "devlop": "^1.0.0", "mdast-util-from-markdown": "^2.0.0", "mdast-util-to-markdown": "^2.0.0" } }, "sha512-IrtvNvjxC1o06taBAVJznEnkiHxLFTzgonUdy8hzFVeDun0uTjxxrRGVaNFqkU1wJR3RBPEfsxmU6jDWPofrTQ=="],
"mdast-util-phrasing": ["mdast-util-phrasing@4.1.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "unist-util-is": "^6.0.0" } }, "sha512-TqICwyvJJpBwvGAMZjj4J2n0X8QWp21b9l0o7eXyVJ25YNWYbJDVIyD1bZXE6WtV6RmKJVYmQAKWa0zWOABz2w=="],
"mdast-util-to-markdown": ["mdast-util-to-markdown@2.1.2", "", { "dependencies": { "@types/mdast": "^4.0.0", "@types/unist": "^3.0.0", "longest-streak": "^3.0.0", "mdast-util-phrasing": "^4.0.0", "mdast-util-to-string": "^4.0.0", "micromark-util-classify-character": "^2.0.0", "micromark-util-decode-string": "^2.0.0", "unist-util-visit": "^5.0.0", "zwitch": "^2.0.0" } }, "sha512-xj68wMTvGXVOKonmog6LwyJKrYXZPvlwabaryTjLh9LuvovB/KAH+kvi8Gjj+7rJjsFi23nkUxRQv1KqSroMqA=="],
"mdast-util-to-string": ["mdast-util-to-string@4.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0" } }, "sha512-0H44vDimn51F0YwvxSJSm0eCDOJTRlmN0R1yBh4HLj9wiV1Dn0QoXGbvFAWj2hSItVTlCmBF1hqKlIyUBVFLPg=="],
"micromark": ["micromark@4.0.2", "", { "dependencies": { "@types/debug": "^4.0.0", "debug": "^4.0.0", "decode-named-character-reference": "^1.0.0", "devlop": "^1.0.0", "micromark-core-commonmark": "^2.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-combine-extensions": "^2.0.0", "micromark-util-decode-numeric-character-reference": "^2.0.0", "micromark-util-encode": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-resolve-all": "^2.0.0", "micromark-util-sanitize-uri": "^2.0.0", "micromark-util-subtokenize": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-zpe98Q6kvavpCr1NPVSCMebCKfD7CA2NqZ+rykeNhONIJBpc1tFKt9hucLGwha3jNTNI8lHpctWJWoimVF4PfA=="],
"micromark-core-commonmark": ["micromark-core-commonmark@2.0.3", "", { "dependencies": { "decode-named-character-reference": "^1.0.0", "devlop": "^1.0.0", "micromark-factory-destination": "^2.0.0", "micromark-factory-label": "^2.0.0", "micromark-factory-space": "^2.0.0", "micromark-factory-title": "^2.0.0", "micromark-factory-whitespace": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-classify-character": "^2.0.0", "micromark-util-html-tag-name": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-resolve-all": "^2.0.0", "micromark-util-subtokenize": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-RDBrHEMSxVFLg6xvnXmb1Ayr2WzLAWjeSATAoxwKYJV94TeNavgoIdA0a9ytzDSVzBy2YKFK+emCPOEibLeCrg=="],
"micromark-extension-frontmatter": ["micromark-extension-frontmatter@2.0.0", "", { "dependencies": { "fault": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-C4AkuM3dA58cgZha7zVnuVxBhDsbttIMiytjgsM2XbHAB2faRVaHRle40558FBN+DJcrLNCoqG5mlrpdU4cRtg=="],
"micromark-extension-gfm": ["micromark-extension-gfm@3.0.0", "", { "dependencies": { "micromark-extension-gfm-autolink-literal": "^2.0.0", "micromark-extension-gfm-footnote": "^2.0.0", "micromark-extension-gfm-strikethrough": "^2.0.0", "micromark-extension-gfm-table": "^2.0.0", "micromark-extension-gfm-tagfilter": "^2.0.0", "micromark-extension-gfm-task-list-item": "^2.0.0", "micromark-util-combine-extensions": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-vsKArQsicm7t0z2GugkCKtZehqUm31oeGBV/KVSorWSy8ZlNAv7ytjFhvaryUiCUJYqs+NoE6AFhpQvBTM6Q4w=="],
"micromark-extension-gfm-autolink-literal": ["micromark-extension-gfm-autolink-literal@2.1.0", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-sanitize-uri": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-oOg7knzhicgQ3t4QCjCWgTmfNhvQbDDnJeVu9v81r7NltNCVmhPy1fJRX27pISafdjL+SVc4d3l48Gb6pbRypw=="],
"micromark-extension-gfm-footnote": ["micromark-extension-gfm-footnote@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-core-commonmark": "^2.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-normalize-identifier": "^2.0.0", "micromark-util-sanitize-uri": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-/yPhxI1ntnDNsiHtzLKYnE3vf9JZ6cAisqVDauhp4CEHxlb4uoOTxOCJ+9s51bIB8U1N1FJ1RXOKTIlD5B/gqw=="],
"micromark-extension-gfm-strikethrough": ["micromark-extension-gfm-strikethrough@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-classify-character": "^2.0.0", "micromark-util-resolve-all": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-ADVjpOOkjz1hhkZLlBiYA9cR2Anf8F4HqZUO6e5eDcPQd0Txw5fxLzzxnEkSkfnD0wziSGiv7sYhk/ktvbf1uw=="],
"micromark-extension-gfm-table": ["micromark-extension-gfm-table@2.1.1", "", { "dependencies": { "devlop": "^1.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-t2OU/dXXioARrC6yWfJ4hqB7rct14e8f7m0cbI5hUmDyyIlwv5vEtooptH8INkbLzOatzKuVbQmAYcbWoyz6Dg=="],
"micromark-extension-gfm-tagfilter": ["micromark-extension-gfm-tagfilter@2.0.0", "", { "dependencies": { "micromark-util-types": "^2.0.0" } }, "sha512-xHlTOmuCSotIA8TW1mDIM6X2O1SiX5P9IuDtqGonFhEK0qgRI4yeC6vMxEV2dgyr2TiD+2PQ10o+cOhdVAcwfg=="],
"micromark-extension-gfm-task-list-item": ["micromark-extension-gfm-task-list-item@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-qIBZhqxqI6fjLDYFTBIa4eivDMnP+OZqsNwmQ3xNLE4Cxwc+zfQEfbs6tzAo2Hjq+bh6q5F+Z8/cksrLFYWQQw=="],
"micromark-factory-destination": ["micromark-factory-destination@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-Xe6rDdJlkmbFRExpTOmRj9N3MaWmbAgdpSrBQvCFqhezUn4AHqJHbaEnfbVYYiexVSs//tqOdY/DxhjdCiJnIA=="],
"micromark-factory-label": ["micromark-factory-label@2.0.1", "", { "dependencies": { "devlop": "^1.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-VFMekyQExqIW7xIChcXn4ok29YE3rnuyveW3wZQWWqF4Nv9Wk5rgJ99KzPvHjkmPXF93FXIbBp6YdW3t71/7Vg=="],
"micromark-factory-space": ["micromark-factory-space@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-zRkxjtBxxLd2Sc0d+fbnEunsTj46SWXgXciZmHq0kDYGnck/ZSGj9/wULTV95uoeYiK5hRXP2mJ98Uo4cq/LQg=="],
"micromark-factory-title": ["micromark-factory-title@2.0.1", "", { "dependencies": { "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-5bZ+3CjhAd9eChYTHsjy6TGxpOFSKgKKJPJxr293jTbfry2KDoWkhBb6TcPVB4NmzaPhMs1Frm9AZH7OD4Cjzw=="],
"micromark-factory-whitespace": ["micromark-factory-whitespace@2.0.1", "", { "dependencies": { "micromark-factory-space": "^2.0.0", "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-Ob0nuZ3PKt/n0hORHyvoD9uZhr+Za8sFoP+OnMcnWK5lngSzALgQYKMr9RJVOWLqQYuyn6ulqGWSXdwf6F80lQ=="],
"micromark-util-character": ["micromark-util-character@2.1.1", "", { "dependencies": { "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-wv8tdUTJ3thSFFFJKtpYKOYiGP2+v96Hvk4Tu8KpCAsTMs6yi+nVmGh1syvSCsaxz45J6Jbw+9DD6g97+NV67Q=="],
"micromark-util-chunked": ["micromark-util-chunked@2.0.1", "", { "dependencies": { "micromark-util-symbol": "^2.0.0" } }, "sha512-QUNFEOPELfmvv+4xiNg2sRYeS/P84pTW0TCgP5zc9FpXetHY0ab7SxKyAQCNCc1eK0459uoLI1y5oO5Vc1dbhA=="],
"micromark-util-classify-character": ["micromark-util-classify-character@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-K0kHzM6afW/MbeWYWLjoHQv1sgg2Q9EccHEDzSkxiP/EaagNzCm7T/WMKZ3rjMbvIpvBiZgwR3dKMygtA4mG1Q=="],
"micromark-util-combine-extensions": ["micromark-util-combine-extensions@2.0.1", "", { "dependencies": { "micromark-util-chunked": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-OnAnH8Ujmy59JcyZw8JSbK9cGpdVY44NKgSM7E9Eh7DiLS2E9RNQf0dONaGDzEG9yjEl5hcqeIsj4hfRkLH/Bg=="],
"micromark-util-decode-numeric-character-reference": ["micromark-util-decode-numeric-character-reference@2.0.2", "", { "dependencies": { "micromark-util-symbol": "^2.0.0" } }, "sha512-ccUbYk6CwVdkmCQMyr64dXz42EfHGkPQlBj5p7YVGzq8I7CtjXZJrubAYezf7Rp+bjPseiROqe7G6foFd+lEuw=="],
"micromark-util-decode-string": ["micromark-util-decode-string@2.0.1", "", { "dependencies": { "decode-named-character-reference": "^1.0.0", "micromark-util-character": "^2.0.0", "micromark-util-decode-numeric-character-reference": "^2.0.0", "micromark-util-symbol": "^2.0.0" } }, "sha512-nDV/77Fj6eH1ynwscYTOsbK7rR//Uj0bZXBwJZRfaLEJ1iGBR6kIfNmlNqaqJf649EP0F3NWNdeJi03elllNUQ=="],
"micromark-util-encode": ["micromark-util-encode@2.0.1", "", {}, "sha512-c3cVx2y4KqUnwopcO9b/SCdo2O67LwJJ/UyqGfbigahfegL9myoEFoDYZgkT7f36T0bLrM9hZTAaAyH+PCAXjw=="],
"micromark-util-html-tag-name": ["micromark-util-html-tag-name@2.0.1", "", {}, "sha512-2cNEiYDhCWKI+Gs9T0Tiysk136SnR13hhO8yW6BGNyhOC4qYFnwF1nKfD3HFAIXA5c45RrIG1ub11GiXeYd1xA=="],
"micromark-util-normalize-identifier": ["micromark-util-normalize-identifier@2.0.1", "", { "dependencies": { "micromark-util-symbol": "^2.0.0" } }, "sha512-sxPqmo70LyARJs0w2UclACPUUEqltCkJ6PhKdMIDuJ3gSf/Q+/GIe3WKl0Ijb/GyH9lOpUkRAO2wp0GVkLvS9Q=="],
"micromark-util-resolve-all": ["micromark-util-resolve-all@2.0.1", "", { "dependencies": { "micromark-util-types": "^2.0.0" } }, "sha512-VdQyxFWFT2/FGJgwQnJYbe1jjQoNTS4RjglmSjTUlpUMa95Htx9NHeYW4rGDJzbjvCsl9eLjMQwGeElsqmzcHg=="],
"micromark-util-sanitize-uri": ["micromark-util-sanitize-uri@2.0.1", "", { "dependencies": { "micromark-util-character": "^2.0.0", "micromark-util-encode": "^2.0.0", "micromark-util-symbol": "^2.0.0" } }, "sha512-9N9IomZ/YuGGZZmQec1MbgxtlgougxTodVwDzzEouPKo3qFWvymFHWcnDi2vzV1ff6kas9ucW+o3yzJK9YB1AQ=="],
"micromark-util-subtokenize": ["micromark-util-subtokenize@2.1.0", "", { "dependencies": { "devlop": "^1.0.0", "micromark-util-chunked": "^2.0.0", "micromark-util-symbol": "^2.0.0", "micromark-util-types": "^2.0.0" } }, "sha512-XQLu552iSctvnEcgXw6+Sx75GflAPNED1qx7eBJ+wydBb2KCbRZe+NwvIEEMM83uml1+2WSXpBAcp9IUCgCYWA=="],
"micromark-util-symbol": ["micromark-util-symbol@2.0.1", "", {}, "sha512-vs5t8Apaud9N28kgCrRUdEed4UJ+wWNvicHLPxCa9ENlYuAY31M0ETy5y1vA33YoNPDFTghEbnh6efaE8h4x0Q=="],
"micromark-util-types": ["micromark-util-types@2.0.2", "", {}, "sha512-Yw0ECSpJoViF1qTU4DC6NwtC4aWGt1EkzaQB8KPPyCRR8z9TWeV0HbEFGTO+ZY1wB22zmxnJqhPyTpOVCpeHTA=="],
"ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
"remark-frontmatter": ["remark-frontmatter@5.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-frontmatter": "^2.0.0", "micromark-extension-frontmatter": "^2.0.0", "unified": "^11.0.0" } }, "sha512-XTFYvNASMe5iPN0719nPrdItC9aU0ssC4v14mH1BCi1u0n1gAocqcujWUrByftZTbLhRtiKRyjYTSIOcr69UVQ=="],
"remark-gfm": ["remark-gfm@4.0.1", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-gfm": "^3.0.0", "micromark-extension-gfm": "^3.0.0", "remark-parse": "^11.0.0", "remark-stringify": "^11.0.0", "unified": "^11.0.0" } }, "sha512-1quofZ2RQ9EWdeN34S79+KExV1764+wCUGop5CPL1WGdD0ocPpu91lzPGbwWMECpEpd42kJGQwzRfyov9j4yNg=="],
"remark-parse": ["remark-parse@11.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-from-markdown": "^2.0.0", "micromark-util-types": "^2.0.0", "unified": "^11.0.0" } }, "sha512-FCxlKLNGknS5ba/1lmpYijMUzX2esxW5xQqjWxw2eHFfS2MSdaHVINFmhjo+qN1WhZhNimq0dZATN9pH0IDrpA=="],
"remark-stringify": ["remark-stringify@11.0.0", "", { "dependencies": { "@types/mdast": "^4.0.0", "mdast-util-to-markdown": "^2.0.0", "unified": "^11.0.0" } }, "sha512-1OSmLd3awB/t8qdoEOMazZkNsfVTeY4fTsgzcQFdXNq8ToTN4ZGwrMnlda4K6smTFKD+GRV6O48i6Z4iKgPPpw=="],
"trough": ["trough@2.2.0", "", {}, "sha512-tmMpK00BjZiUyVyvrBK7knerNgmgvcV/KLVyuma/SC+TQN167GrMRciANTz09+k3zW8L8t60jWO1GpfkZdjTaw=="],
"unified": ["unified@11.0.5", "", { "dependencies": { "@types/unist": "^3.0.0", "bail": "^2.0.0", "devlop": "^1.0.0", "extend": "^3.0.0", "is-plain-obj": "^4.0.0", "trough": "^2.0.0", "vfile": "^6.0.0" } }, "sha512-xKvGhPWw3k84Qjh8bI3ZeJjqnyadK+GEFtazSfZv/rKeTkTjOJho6mFqh2SM96iIcZokxiOpg78GazTSg8+KHA=="],
"unist-util-is": ["unist-util-is@6.0.1", "", { "dependencies": { "@types/unist": "^3.0.0" } }, "sha512-LsiILbtBETkDz8I9p1dQ0uyRUWuaQzd/cuEeS1hoRSyW5E5XGmTzlwY1OrNzzakGowI9Dr/I8HVaw4hTtnxy8g=="],
"unist-util-stringify-position": ["unist-util-stringify-position@4.0.0", "", { "dependencies": { "@types/unist": "^3.0.0" } }, "sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ=="],
"unist-util-visit": ["unist-util-visit@5.1.0", "", { "dependencies": { "@types/unist": "^3.0.0", "unist-util-is": "^6.0.0", "unist-util-visit-parents": "^6.0.0" } }, "sha512-m+vIdyeCOpdr/QeQCu2EzxX/ohgS8KbnPDgFni4dQsfSCtpz8UqDyY5GjRru8PDKuYn7Fq19j1CQ+nJSsGKOzg=="],
"unist-util-visit-parents": ["unist-util-visit-parents@6.0.2", "", { "dependencies": { "@types/unist": "^3.0.0", "unist-util-is": "^6.0.0" } }, "sha512-goh1s1TBrqSqukSc8wrjwWhL0hiJxgA8m4kFxGlQ+8FYQ3C/m11FcTs4YYem7V664AhHVvgoQLk890Ssdsr2IQ=="],
"vfile": ["vfile@6.0.3", "", { "dependencies": { "@types/unist": "^3.0.0", "vfile-message": "^4.0.0" } }, "sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q=="],
"vfile-message": ["vfile-message@4.0.3", "", { "dependencies": { "@types/unist": "^3.0.0", "unist-util-stringify-position": "^4.0.0" } }, "sha512-QTHzsGd1EhbZs4AsQ20JX1rC3cOlt/IWJruk893DfLRr57lcnOeMaWG4K0JrRta4mIJZKth2Au3mM3u03/JWKw=="],
"zwitch": ["zwitch@2.0.4", "", {}, "sha512-bXE4cR/kVZhKZX/RjPEflHaKVhUVl85noU3v6b8apfQEc1x4A+zBxjZ4lN8LqGd6WZ3dl98pY4o717VFmoPp+A=="],
}
}
+132
View File
@@ -0,0 +1,132 @@
import { readFileSync, writeFileSync, mkdirSync } from "fs"
import { basename, dirname, join } from "path"
import { unified } from "unified"
import remarkParse from "remark-parse"
import remarkGfm from "remark-gfm"
import remarkFrontmatter from "remark-frontmatter"
import remarkStringify from "remark-stringify"
import type { Root, Content } from "mdast"
const args = process.argv.slice(2)
const file = args.find(a => !a.startsWith("--"))
const maxWords = parseInt(args[args.indexOf("--max-words") + 1] || "5000")
if (!file) {
console.error("Usage: chunk.ts <file> [--max-words 5000]")
process.exit(1)
}
const content = readFileSync(file, "utf-8")
const tree = unified()
.use(remarkParse)
.use(remarkGfm)
.use(remarkFrontmatter, ["yaml"])
.parse(content)
const stringify = unified()
.use(remarkStringify, { bullet: "-", emphasis: "*", strong: "*" })
.use(remarkGfm)
.use(remarkFrontmatter, ["yaml"])
function nodeToMd(node: Content): string {
const root: Root = { type: "root", children: [node] }
return stringify.stringify(root).trim()
}
function countWords(text: string): number {
const cleaned = text.replace(/[#*`\[\]()>|_~-]/g, " ")
const cjk = cleaned.match(/[\u4e00-\u9fff\u3400-\u4dbf\uf900-\ufaff]/g)
const latin = cleaned.match(/[a-zA-Z0-9]+/g)
return (cjk?.length || 0) + (latin?.length || 0)
}
interface Block {
md: string
words: number
}
function splitNodeToBlocks(node: Content): Block[] {
const md = nodeToMd(node)
const words = countWords(md)
if (words <= maxWords) return [{ md, words }]
if (node.type === "heading" || node.type === "thematicBreak" || node.type === "html") {
return [{ md, words }]
}
if ("children" in node && Array.isArray(node.children)) {
const blocks: Block[] = []
for (const child of node.children as Content[]) {
blocks.push(...splitNodeToBlocks(child))
}
return blocks
}
const lines = md.split("\n")
if (lines.length > 1) {
const blocks: Block[] = []
let buf: string[] = []
let bufWords = 0
for (const line of lines) {
const lw = countWords(line)
if (bufWords + lw > maxWords && buf.length > 0) {
blocks.push({ md: buf.join("\n"), words: bufWords })
buf = [line]
bufWords = lw
} else {
buf.push(line)
bufWords += lw
}
}
if (buf.length > 0) blocks.push({ md: buf.join("\n"), words: bufWords })
return blocks
}
return [{ md, words }]
}
let frontmatter = ""
const blocks: Block[] = []
for (const node of tree.children) {
if (node.type === "yaml") {
frontmatter = `---\n${node.value}\n---`
continue
}
blocks.push(...splitNodeToBlocks(node as Content))
}
const chunks: { blocks: Block[]; words: number }[] = []
let cur: Block[] = []
let curWords = 0
for (const b of blocks) {
if (curWords + b.words > maxWords && cur.length > 0) {
chunks.push({ blocks: cur, words: curWords })
cur = [b]
curWords = b.words
} else {
cur.push(b)
curWords += b.words
}
}
if (cur.length > 0) chunks.push({ blocks: cur, words: curWords })
const dir = join(dirname(file), "chunks")
mkdirSync(dir, { recursive: true })
chunks.forEach((chunk, i) => {
const num = String(i + 1).padStart(2, "0")
const out = join(dir, `chunk-${num}.md`)
writeFileSync(out, chunk.blocks.map(b => b.md).join("\n\n"))
})
console.log(JSON.stringify({
source: file,
chunks: chunks.length,
output_dir: dir,
frontmatter: !!frontmatter,
words_per_chunk: chunks.map(c => c.words)
}))
@@ -0,0 +1,9 @@
{
"dependencies": {
"remark-frontmatter": "^5.0.0",
"remark-gfm": "^4.0.1",
"remark-parse": "^11.0.0",
"remark-stringify": "^11.0.0",
"unified": "^11.0.5"
}
}