Add support for reading PDF and docx files

This commit is contained in:
Saoud Rizwan
2024-08-31 02:21:23 -04:00
parent 5a05279a4d
commit 1d87bcf767
4 changed files with 195 additions and 14 deletions

164
package-lock.json generated
View File

@@ -13,6 +13,7 @@
"@anthropic-ai/sdk": "^0.26.0", "@anthropic-ai/sdk": "^0.26.0",
"@anthropic-ai/vertex-sdk": "^0.4.1", "@anthropic-ai/vertex-sdk": "^0.4.1",
"@types/clone-deep": "^4.0.4", "@types/clone-deep": "^4.0.4",
"@types/pdf-parse": "^1.1.4",
"@vscode/codicons": "^0.0.36", "@vscode/codicons": "^0.0.36",
"axios": "^1.7.4", "axios": "^1.7.4",
"clone-deep": "^4.0.1", "clone-deep": "^4.0.1",
@@ -21,9 +22,12 @@
"diff": "^5.2.0", "diff": "^5.2.0",
"execa": "^9.3.0", "execa": "^9.3.0",
"globby": "^14.0.2", "globby": "^14.0.2",
"isbinaryfile": "^5.0.2",
"mammoth": "^1.8.0",
"openai": "^4.54.0", "openai": "^4.54.0",
"os-name": "^6.0.0", "os-name": "^6.0.0",
"p-wait-for": "^5.0.2", "p-wait-for": "^5.0.2",
"pdf-parse": "^1.1.1",
"serialize-error": "^11.0.3", "serialize-error": "^11.0.3",
"tree-kill": "^1.2.2", "tree-kill": "^1.2.2",
"tree-sitter-wasms": "^0.1.11", "tree-sitter-wasms": "^0.1.11",
@@ -4536,6 +4540,12 @@
"form-data": "^4.0.0" "form-data": "^4.0.0"
} }
}, },
"node_modules/@types/pdf-parse": {
"version": "1.1.4",
"resolved": "https://registry.npmjs.org/@types/pdf-parse/-/pdf-parse-1.1.4.tgz",
"integrity": "sha512-+gbBHbNCVGGYw1S9lAIIvrHW47UYOhMIFUsJcMkMrzy1Jf0vulBN3XQIjPgnoOXveMuHnF3b57fXROnY/Or7eg==",
"license": "MIT"
},
"node_modules/@types/vscode": { "node_modules/@types/vscode": {
"version": "1.91.0", "version": "1.91.0",
"resolved": "https://registry.npmjs.org/@types/vscode/-/vscode-1.91.0.tgz", "resolved": "https://registry.npmjs.org/@types/vscode/-/vscode-1.91.0.tgz",
@@ -4819,6 +4829,15 @@
"node": ">=16" "node": ">=16"
} }
}, },
"node_modules/@xmldom/xmldom": {
"version": "0.8.10",
"resolved": "https://registry.npmjs.org/@xmldom/xmldom/-/xmldom-0.8.10.tgz",
"integrity": "sha512-2WALfTl4xo2SkGCYRt6rDTFfk9R1czmBvUQy12gK2KuRKIpWEhcbbzy8EZXtz/jkRqHX8bFEc6FC1HjX4TUWYw==",
"license": "MIT",
"engines": {
"node": ">=10.0.0"
}
},
"node_modules/abort-controller": { "node_modules/abort-controller": {
"version": "3.0.0", "version": "3.0.0",
"resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz", "resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
@@ -5108,6 +5127,12 @@
"node": ">= 6" "node": ">= 6"
} }
}, },
"node_modules/bluebird": {
"version": "3.4.7",
"resolved": "https://registry.npmjs.org/bluebird/-/bluebird-3.4.7.tgz",
"integrity": "sha512-iD3898SR7sWVRHbiQv+sHUtHnMvC1o3nW5rAcqnq3uOn07DSAppZYUkIGslDz6gXC7HfunPe7YVBgoEJASPcHA==",
"license": "MIT"
},
"node_modules/bowser": { "node_modules/bowser": {
"version": "2.11.0", "version": "2.11.0",
"resolved": "https://registry.npmjs.org/bowser/-/bowser-2.11.0.tgz", "resolved": "https://registry.npmjs.org/bowser/-/bowser-2.11.0.tgz",
@@ -5443,7 +5468,6 @@
"version": "1.0.3", "version": "1.0.3",
"resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.3.tgz", "resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.3.tgz",
"integrity": "sha512-ZQBvi1DcpJ4GDqanjucZ2Hj3wEO5pZDS89BWbkcrvdxksJorwUDDZamX9ldFkp9aw2lmBDLgkObEA4DWNJ9FYQ==", "integrity": "sha512-ZQBvi1DcpJ4GDqanjucZ2Hj3wEO5pZDS89BWbkcrvdxksJorwUDDZamX9ldFkp9aw2lmBDLgkObEA4DWNJ9FYQ==",
"dev": true,
"license": "MIT" "license": "MIT"
}, },
"node_modules/cross-spawn": { "node_modules/cross-spawn": {
@@ -5628,6 +5652,12 @@
"node": ">=0.3.1" "node": ">=0.3.1"
} }
}, },
"node_modules/dingbat-to-unicode": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/dingbat-to-unicode/-/dingbat-to-unicode-1.0.1.tgz",
"integrity": "sha512-98l0sW87ZT58pU4i61wa2OHwxbiYSbuxsCBozaVnYX2iCnr3bLM3fIes1/ej7h1YdOKuKt/MLs706TVnALA65w==",
"license": "BSD-2-Clause"
},
"node_modules/dir-glob": { "node_modules/dir-glob": {
"version": "3.0.1", "version": "3.0.1",
"resolved": "https://registry.npmjs.org/dir-glob/-/dir-glob-3.0.1.tgz", "resolved": "https://registry.npmjs.org/dir-glob/-/dir-glob-3.0.1.tgz",
@@ -5662,6 +5692,15 @@
"node": ">=6.0.0" "node": ">=6.0.0"
} }
}, },
"node_modules/duck": {
"version": "0.1.12",
"resolved": "https://registry.npmjs.org/duck/-/duck-0.1.12.tgz",
"integrity": "sha512-wkctla1O6VfP89gQ+J/yDesM0S7B7XLXjKGzXxMDVFg7uEn706niAtyYovKbyq1oT9YwDcly721/iUWoc8MVRg==",
"license": "BSD",
"dependencies": {
"underscore": "^1.13.1"
}
},
"node_modules/eastasianwidth": { "node_modules/eastasianwidth": {
"version": "0.2.0", "version": "0.2.0",
"resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz", "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz",
@@ -6903,7 +6942,6 @@
"version": "3.0.6", "version": "3.0.6",
"resolved": "https://registry.npmjs.org/immediate/-/immediate-3.0.6.tgz", "resolved": "https://registry.npmjs.org/immediate/-/immediate-3.0.6.tgz",
"integrity": "sha512-XXOFtyqDjNDAQxVfYxuF7g9Il/IbWmmlQg2MYKOH8ExIT1qg6xc4zyS3HaEEATgs1btfzxq15ciUiY7gjSXRGQ==", "integrity": "sha512-XXOFtyqDjNDAQxVfYxuF7g9Il/IbWmmlQg2MYKOH8ExIT1qg6xc4zyS3HaEEATgs1btfzxq15ciUiY7gjSXRGQ==",
"dev": true,
"license": "MIT" "license": "MIT"
}, },
"node_modules/import-fresh": { "node_modules/import-fresh": {
@@ -6949,7 +6987,6 @@
"version": "2.0.4", "version": "2.0.4",
"resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz", "resolved": "https://registry.npmjs.org/inherits/-/inherits-2.0.4.tgz",
"integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==", "integrity": "sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==",
"dev": true,
"license": "ISC" "license": "ISC"
}, },
"node_modules/internal-slot": { "node_modules/internal-slot": {
@@ -7331,9 +7368,20 @@
"version": "1.0.0", "version": "1.0.0",
"resolved": "https://registry.npmjs.org/isarray/-/isarray-1.0.0.tgz", "resolved": "https://registry.npmjs.org/isarray/-/isarray-1.0.0.tgz",
"integrity": "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ==", "integrity": "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ==",
"dev": true,
"license": "MIT" "license": "MIT"
}, },
"node_modules/isbinaryfile": {
"version": "5.0.2",
"resolved": "https://registry.npmjs.org/isbinaryfile/-/isbinaryfile-5.0.2.tgz",
"integrity": "sha512-GvcjojwonMjWbTkfMpnVHVqXW/wKMYDfEpY94/8zy8HFMOqb/VL6oeONq9v87q4ttVlaTLnGXnJD4B5B1OTGIg==",
"license": "MIT",
"engines": {
"node": ">= 18.0.0"
},
"funding": {
"url": "https://github.com/sponsors/gjtorikian/"
}
},
"node_modules/isexe": { "node_modules/isexe": {
"version": "2.0.0", "version": "2.0.0",
"resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz", "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
@@ -7472,7 +7520,6 @@
"version": "3.10.1", "version": "3.10.1",
"resolved": "https://registry.npmjs.org/jszip/-/jszip-3.10.1.tgz", "resolved": "https://registry.npmjs.org/jszip/-/jszip-3.10.1.tgz",
"integrity": "sha512-xXDvecyTpGLrqFrvkrUSoxxfJI5AH7U8zxxtVclpsUtMCq4JQ290LY8AW5c7Ggnr/Y/oK+bQMbqK2qmtk3pN4g==", "integrity": "sha512-xXDvecyTpGLrqFrvkrUSoxxfJI5AH7U8zxxtVclpsUtMCq4JQ290LY8AW5c7Ggnr/Y/oK+bQMbqK2qmtk3pN4g==",
"dev": true,
"license": "(MIT OR GPL-3.0-or-later)", "license": "(MIT OR GPL-3.0-or-later)",
"dependencies": { "dependencies": {
"lie": "~3.3.0", "lie": "~3.3.0",
@@ -7536,7 +7583,6 @@
"version": "3.3.0", "version": "3.3.0",
"resolved": "https://registry.npmjs.org/lie/-/lie-3.3.0.tgz", "resolved": "https://registry.npmjs.org/lie/-/lie-3.3.0.tgz",
"integrity": "sha512-UaiMJzeWRlEujzAuw5LokY1L5ecNQYZKfmyZ9L7wDHb/p5etKaxXhohBcrw0EYby+G/NA52vRSN4N39dxHAIwQ==", "integrity": "sha512-UaiMJzeWRlEujzAuw5LokY1L5ecNQYZKfmyZ9L7wDHb/p5etKaxXhohBcrw0EYby+G/NA52vRSN4N39dxHAIwQ==",
"dev": true,
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"immediate": "~3.0.5" "immediate": "~3.0.5"
@@ -7598,6 +7644,17 @@
"url": "https://github.com/sponsors/sindresorhus" "url": "https://github.com/sponsors/sindresorhus"
} }
}, },
"node_modules/lop": {
"version": "0.4.1",
"resolved": "https://registry.npmjs.org/lop/-/lop-0.4.1.tgz",
"integrity": "sha512-9xyho9why2A2tzm5aIcMWKvzqKsnxrf9B5I+8O30olh6lQU8PH978LqZoI4++37RBgS1Em5i54v1TFs/3wnmXQ==",
"license": "BSD-2-Clause",
"dependencies": {
"duck": "^0.1.12",
"option": "~0.2.1",
"underscore": "^1.13.1"
}
},
"node_modules/lru-cache": { "node_modules/lru-cache": {
"version": "10.3.0", "version": "10.3.0",
"resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.3.0.tgz", "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.3.0.tgz",
@@ -7636,6 +7693,39 @@
"url": "https://github.com/sponsors/sindresorhus" "url": "https://github.com/sponsors/sindresorhus"
} }
}, },
"node_modules/mammoth": {
"version": "1.8.0",
"resolved": "https://registry.npmjs.org/mammoth/-/mammoth-1.8.0.tgz",
"integrity": "sha512-pJNfxSk9IEGVpau+tsZFz22ofjUsl2mnA5eT8PjPs2n0BP+rhVte4Nez6FdgEuxv3IGI3afiV46ImKqTGDVlbA==",
"license": "BSD-2-Clause",
"dependencies": {
"@xmldom/xmldom": "^0.8.6",
"argparse": "~1.0.3",
"base64-js": "^1.5.1",
"bluebird": "~3.4.0",
"dingbat-to-unicode": "^1.0.1",
"jszip": "^3.7.1",
"lop": "^0.4.1",
"path-is-absolute": "^1.0.0",
"underscore": "^1.13.1",
"xmlbuilder": "^10.0.0"
},
"bin": {
"mammoth": "bin/mammoth"
},
"engines": {
"node": ">=12.0.0"
}
},
"node_modules/mammoth/node_modules/argparse": {
"version": "1.0.10",
"resolved": "https://registry.npmjs.org/argparse/-/argparse-1.0.10.tgz",
"integrity": "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==",
"license": "MIT",
"dependencies": {
"sprintf-js": "~1.0.2"
}
},
"node_modules/memorystream": { "node_modules/memorystream": {
"version": "0.3.1", "version": "0.3.1",
"resolved": "https://registry.npmjs.org/memorystream/-/memorystream-0.3.1.tgz", "resolved": "https://registry.npmjs.org/memorystream/-/memorystream-0.3.1.tgz",
@@ -7943,6 +8033,12 @@
"node": ">=10.5.0" "node": ">=10.5.0"
} }
}, },
"node_modules/node-ensure": {
"version": "0.0.0",
"resolved": "https://registry.npmjs.org/node-ensure/-/node-ensure-0.0.0.tgz",
"integrity": "sha512-DRI60hzo2oKN1ma0ckc6nQWlHU69RH6xN0sjQTjMpChPfTYvKZdcQFfdYK2RWbJcKyUizSIy/l8OTGxMAM1QDw==",
"license": "MIT"
},
"node_modules/node-fetch": { "node_modules/node-fetch": {
"version": "2.7.0", "version": "2.7.0",
"resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz", "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
@@ -8317,6 +8413,12 @@
"undici-types": "~5.26.4" "undici-types": "~5.26.4"
} }
}, },
"node_modules/option": {
"version": "0.2.4",
"resolved": "https://registry.npmjs.org/option/-/option-0.2.4.tgz",
"integrity": "sha512-pkEqbDyl8ou5cpq+VsnQbe/WlEy5qS7xPzMS1U55OCG9KPvwFD46zDbxQIj3egJSFc3D+XhYOPUzz49zQAVy7A==",
"license": "BSD-2-Clause"
},
"node_modules/optionator": { "node_modules/optionator": {
"version": "0.9.4", "version": "0.9.4",
"resolved": "https://registry.npmjs.org/optionator/-/optionator-0.9.4.tgz", "resolved": "https://registry.npmjs.org/optionator/-/optionator-0.9.4.tgz",
@@ -8542,7 +8644,6 @@
"version": "1.0.11", "version": "1.0.11",
"resolved": "https://registry.npmjs.org/pako/-/pako-1.0.11.tgz", "resolved": "https://registry.npmjs.org/pako/-/pako-1.0.11.tgz",
"integrity": "sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw==", "integrity": "sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw==",
"dev": true,
"license": "(MIT AND Zlib)" "license": "(MIT AND Zlib)"
}, },
"node_modules/parent-module": { "node_modules/parent-module": {
@@ -8598,7 +8699,6 @@
"version": "1.0.1", "version": "1.0.1",
"resolved": "https://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz", "resolved": "https://registry.npmjs.org/path-is-absolute/-/path-is-absolute-1.0.1.tgz",
"integrity": "sha512-AVbw3UJ2e9bq64vSaS9Am0fje1Pa8pbGqTTsmXfaIiMpnr5DlDhfJOuLj9Sf95ZPVDAUerDfEk88MPmPe7UCQg==", "integrity": "sha512-AVbw3UJ2e9bq64vSaS9Am0fje1Pa8pbGqTTsmXfaIiMpnr5DlDhfJOuLj9Sf95ZPVDAUerDfEk88MPmPe7UCQg==",
"dev": true,
"license": "MIT", "license": "MIT",
"engines": { "engines": {
"node": ">=0.10.0" "node": ">=0.10.0"
@@ -8648,6 +8748,28 @@
"url": "https://github.com/sponsors/sindresorhus" "url": "https://github.com/sponsors/sindresorhus"
} }
}, },
"node_modules/pdf-parse": {
"version": "1.1.1",
"resolved": "https://registry.npmjs.org/pdf-parse/-/pdf-parse-1.1.1.tgz",
"integrity": "sha512-v6ZJ/efsBpGrGGknjtq9J/oC8tZWq0KWL5vQrk2GlzLEQPUDB1ex+13Rmidl1neNN358Jn9EHZw5y07FFtaC7A==",
"license": "MIT",
"dependencies": {
"debug": "^3.1.0",
"node-ensure": "^0.0.0"
},
"engines": {
"node": ">=6.8.1"
}
},
"node_modules/pdf-parse/node_modules/debug": {
"version": "3.2.7",
"resolved": "https://registry.npmjs.org/debug/-/debug-3.2.7.tgz",
"integrity": "sha512-CFjzYYAi4ThfiQvizrFQevTTXHtnCqWfe7x1AhgEscTz6ZbLbfoLRLPugTQyBth6f8ZERVUSyWHFD/7Wu4t1XQ==",
"license": "MIT",
"dependencies": {
"ms": "^2.1.1"
}
},
"node_modules/picomatch": { "node_modules/picomatch": {
"version": "2.3.1", "version": "2.3.1",
"resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz", "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-2.3.1.tgz",
@@ -8722,7 +8844,6 @@
"version": "2.0.1", "version": "2.0.1",
"resolved": "https://registry.npmjs.org/process-nextick-args/-/process-nextick-args-2.0.1.tgz", "resolved": "https://registry.npmjs.org/process-nextick-args/-/process-nextick-args-2.0.1.tgz",
"integrity": "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==", "integrity": "sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==",
"dev": true,
"license": "MIT" "license": "MIT"
}, },
"node_modules/proxy-from-env": { "node_modules/proxy-from-env": {
@@ -8802,7 +8923,6 @@
"version": "2.3.8", "version": "2.3.8",
"resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-2.3.8.tgz", "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-2.3.8.tgz",
"integrity": "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==", "integrity": "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==",
"dev": true,
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"core-util-is": "~1.0.0", "core-util-is": "~1.0.0",
@@ -9142,7 +9262,6 @@
"version": "1.0.5", "version": "1.0.5",
"resolved": "https://registry.npmjs.org/setimmediate/-/setimmediate-1.0.5.tgz", "resolved": "https://registry.npmjs.org/setimmediate/-/setimmediate-1.0.5.tgz",
"integrity": "sha512-MATJdZp8sLqDl/68LfQmbP8zKPLQNV6BIZoIgrscFDQ+RsvK/BxeDQOgyxKKoh0y/8h3BqVFnCqQ/gd+reiIXA==", "integrity": "sha512-MATJdZp8sLqDl/68LfQmbP8zKPLQNV6BIZoIgrscFDQ+RsvK/BxeDQOgyxKKoh0y/8h3BqVFnCqQ/gd+reiIXA==",
"dev": true,
"license": "MIT" "license": "MIT"
}, },
"node_modules/shallow-clone": { "node_modules/shallow-clone": {
@@ -9265,6 +9384,12 @@
"dev": true, "dev": true,
"license": "CC0-1.0" "license": "CC0-1.0"
}, },
"node_modules/sprintf-js": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz",
"integrity": "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g==",
"license": "BSD-3-Clause"
},
"node_modules/stdin-discarder": { "node_modules/stdin-discarder": {
"version": "0.1.0", "version": "0.1.0",
"resolved": "https://registry.npmjs.org/stdin-discarder/-/stdin-discarder-0.1.0.tgz", "resolved": "https://registry.npmjs.org/stdin-discarder/-/stdin-discarder-0.1.0.tgz",
@@ -9285,7 +9410,6 @@
"version": "1.1.1", "version": "1.1.1",
"resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.1.1.tgz", "resolved": "https://registry.npmjs.org/string_decoder/-/string_decoder-1.1.1.tgz",
"integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==", "integrity": "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg==",
"dev": true,
"license": "MIT", "license": "MIT",
"dependencies": { "dependencies": {
"safe-buffer": "~5.1.0" "safe-buffer": "~5.1.0"
@@ -9785,6 +9909,12 @@
"url": "https://github.com/sponsors/ljharb" "url": "https://github.com/sponsors/ljharb"
} }
}, },
"node_modules/underscore": {
"version": "1.13.7",
"resolved": "https://registry.npmjs.org/underscore/-/underscore-1.13.7.tgz",
"integrity": "sha512-GMXzWtsc57XAtguZgaQViUOzs0KTkk8ojr3/xAxXLITqf/3EMwxC0inyETfDFjH/Krbhuep0HNbbjI9i/q3F3g==",
"license": "MIT"
},
"node_modules/undici-types": { "node_modules/undici-types": {
"version": "5.26.5", "version": "5.26.5",
"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz", "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
@@ -9816,7 +9946,6 @@
"version": "1.0.2", "version": "1.0.2",
"resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz", "resolved": "https://registry.npmjs.org/util-deprecate/-/util-deprecate-1.0.2.tgz",
"integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==", "integrity": "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==",
"dev": true,
"license": "MIT" "license": "MIT"
}, },
"node_modules/uuid": { "node_modules/uuid": {
@@ -10165,6 +10294,15 @@
"dev": true, "dev": true,
"license": "ISC" "license": "ISC"
}, },
"node_modules/xmlbuilder": {
"version": "10.1.1",
"resolved": "https://registry.npmjs.org/xmlbuilder/-/xmlbuilder-10.1.1.tgz",
"integrity": "sha512-OyzrcFLL/nb6fMGHbiRDuPup9ljBycsdCypwuyg5AAHvyWzGfChJpCXMG88AGTIMFhGZ9RccFN1e6lhg3hkwKg==",
"license": "MIT",
"engines": {
"node": ">=4.0"
}
},
"node_modules/y18n": { "node_modules/y18n": {
"version": "5.0.8", "version": "5.0.8",
"resolved": "https://registry.npmjs.org/y18n/-/y18n-5.0.8.tgz", "resolved": "https://registry.npmjs.org/y18n/-/y18n-5.0.8.tgz",

View File

@@ -136,6 +136,7 @@
"@anthropic-ai/sdk": "^0.26.0", "@anthropic-ai/sdk": "^0.26.0",
"@anthropic-ai/vertex-sdk": "^0.4.1", "@anthropic-ai/vertex-sdk": "^0.4.1",
"@types/clone-deep": "^4.0.4", "@types/clone-deep": "^4.0.4",
"@types/pdf-parse": "^1.1.4",
"@vscode/codicons": "^0.0.36", "@vscode/codicons": "^0.0.36",
"axios": "^1.7.4", "axios": "^1.7.4",
"clone-deep": "^4.0.1", "clone-deep": "^4.0.1",
@@ -144,9 +145,12 @@
"diff": "^5.2.0", "diff": "^5.2.0",
"execa": "^9.3.0", "execa": "^9.3.0",
"globby": "^14.0.2", "globby": "^14.0.2",
"isbinaryfile": "^5.0.2",
"mammoth": "^1.8.0",
"openai": "^4.54.0", "openai": "^4.54.0",
"os-name": "^6.0.0", "os-name": "^6.0.0",
"p-wait-for": "^5.0.2", "p-wait-for": "^5.0.2",
"pdf-parse": "^1.1.1",
"serialize-error": "^11.0.3", "serialize-error": "^11.0.3",
"tree-kill": "^1.2.2", "tree-kill": "^1.2.2",
"tree-sitter-wasms": "^0.1.11", "tree-sitter-wasms": "^0.1.11",

View File

@@ -27,6 +27,7 @@ import { ClaudeAskResponse } from "./shared/WebviewMessage"
import { findLast, findLastIndex } from "./utils" import { findLast, findLastIndex } from "./utils"
import { truncateHalfConversation } from "./utils/context-management" import { truncateHalfConversation } from "./utils/context-management"
import { regexSearchFiles } from "./utils/ripgrep" import { regexSearchFiles } from "./utils/ripgrep"
import { extractTextFromFile } from "./utils/extract-text"
const SYSTEM_PROMPT = const SYSTEM_PROMPT =
() => `You are Claude Dev, a highly skilled software developer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices. () => `You are Claude Dev, a highly skilled software developer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
@@ -924,7 +925,7 @@ export class ClaudeDev {
} }
try { try {
const absolutePath = path.resolve(cwd, relPath) const absolutePath = path.resolve(cwd, relPath)
const content = await fs.readFile(absolutePath, "utf-8") const content = await extractTextFromFile(absolutePath)
const message = JSON.stringify({ const message = JSON.stringify({
tool: "readFile", tool: "readFile",

38
src/utils/extract-text.ts Normal file
View File

@@ -0,0 +1,38 @@
import * as path from "path"
import pdf from "pdf-parse"
import mammoth from "mammoth"
import { isBinaryFile } from "isbinaryfile"
import fs from "fs/promises"
export async function extractTextFromFile(filePath: string): Promise<string> {
try {
await fs.access(filePath)
} catch (error) {
throw new Error(`File not found: ${filePath}`)
}
const fileExtension = path.extname(filePath).toLowerCase()
switch (fileExtension) {
case ".pdf":
return extractTextFromPDF(filePath)
case ".docx":
return extractTextFromDOCX(filePath)
default:
const isBinary = await isBinaryFile(filePath)
if (!isBinary) {
return await fs.readFile(filePath, "utf8")
} else {
throw new Error(`Unsupported file type: ${fileExtension}`)
}
}
}
async function extractTextFromPDF(filePath: string): Promise<string> {
const dataBuffer = await fs.readFile(filePath)
const data = await pdf(dataBuffer)
return data.text
}
async function extractTextFromDOCX(filePath: string): Promise<string> {
const result = await mammoth.extractRawText({ path: filePath })
return result.value
}