Wire pdfjs cmaps + standard fonts so text layer positions correctly

Strong likelihood that the "text layer is misplaced / body text not selectable" symptoms across multiple PDFs come from PDF.js falling back to substitute font metrics. Without the cmaps directory (CID character maps for non-Latin fonts) and the standard_fonts directory (Helvetica/Times/Courier metrics for unembedded standard fonts), the canvas glyphs use embedded font data while the text-layer span positions are computed from fallback metrics. The two diverge — text spans land in the wrong place, or text content can't be decoded at all, leaving the body unselectable. Both directories are now copied into the served root by vite-plugin-static-copy and passed to pdfjs.getDocument() as `cMapUrl: "/cmaps/"` + `cMapPacked: true` + `standardFontDataUrl: "/standard_fonts/"` via PdfLoader's `document` prop (which accepts a full DocumentInitParameters object). If this is the right diagnosis, the textLayer overlay should now line up with the visible glyphs on the same PDFs that were producing fragmented captures. If the body text is still unselectable, the PDF genuinely lacks a text layer for those glyphs (image-only content) and OCR would be the only path forward. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-27 00:38:34 +02:00
parent 3834f5c209
commit c000ce6f73
4 changed files with 229 additions and 2 deletions
--- a/package.json
+++ b/package.json
@@ -42,6 +42,7 @@
    "typescript": "^5.5.4",
    "typescript-eslint": "^8.0.0",
    "vite": "^5.4.0",
+    "vite-plugin-static-copy": "^2",
    "vitest": "^2.0.5"
  }
 }
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -72,6 +72,9 @@ importers:
      vite:
        specifier: ^5.4.0
        version: 5.4.21(@types/node@20.19.41)
+      vite-plugin-static-copy:
+        specifier: ^2
+        version: 2.3.2(vite@5.4.21(@types/node@20.19.41))
      vitest:
        specifier: ^2.0.5
        version: 2.1.9(@types/node@20.19.41)(happy-dom@20.9.0)
@@ -477,6 +480,18 @@ packages:
      '@emnapi/core': ^1.7.1
      '@emnapi/runtime': ^1.7.1

+  '@nodelib/fs.scandir@2.1.5':
+    resolution: {integrity: sha512-vq24Bq3ym5HEQm2NKCr3yXDwjc7vTsEThRDnkp2DK9p1uqLR+DHurm/NOTo0KG7HYHU7eppKZj3MyqYuMBf62g==}
+    engines: {node: '>= 8'}
+
+  '@nodelib/fs.stat@2.0.5':
+    resolution: {integrity: sha512-RkhPPp2zrqDAQA/2jNhnztcPAlv64XdhIp7a7454A5ovI7Bukxgt7MX7udwAu3zg1DcpPU0rz3VV1SeaqvY4+A==}
+    engines: {node: '>= 8'}
+
+  '@nodelib/fs.walk@1.2.8':
+    resolution: {integrity: sha512-oGB+UxlgWcgQkgwo8GcEGwemoTFt3FIO9ababBmaGwXIoBKZ+GTy0pP185beGg7Llih/NSHSV2XAs1lnznocSg==}
+    engines: {node: '>= 8'}
+
  '@nolyfill/is-core-module@1.0.39':
    resolution: {integrity: sha512-nn5ozdjYQpUCZlWGuxcJY/KpxkWQs4DcbMCmKojjyrYDEAGy4Ce19NN4v5MduafTwJlbKc99UA8YhSVqq9yPZA==}
    engines: {node: '>=12.4.0'}
@@ -1374,6 +1389,10 @@ packages:
    resolution: {integrity: sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==}
    engines: {node: '>=10'}

+  anymatch@3.1.3:
+    resolution: {integrity: sha512-KMReFUr0B4t+D+OBkjR3KYqvocp2XaSzO55UcB6mgQMd3KbcE+mWTyvVV7D/zsdEbNnV6acZUutkiHQXvTr1Rw==}
+    engines: {node: '>= 8'}
+
  argparse@2.0.1:
    resolution: {integrity: sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q==}

@@ -1432,6 +1451,10 @@ packages:
    engines: {node: '>=6.0.0'}
    hasBin: true

+  binary-extensions@2.3.0:
+    resolution: {integrity: sha512-Ceh+7ox5qe7LJuLHoY0feh3pHuUDHAcRUeyL2VYghZwfpkNIy/+8Ocg0a3UuSoYzavmylwuLWQOf3hl0jjMMIw==}
+    engines: {node: '>=8'}
+
  brace-expansion@1.1.14:
    resolution: {integrity: sha512-MWPGfDxnyzKU7rNOW9SP/c50vi3xrmrua/+6hfPbCS2ABNWfx24vPidzvC7krjU/RTo235sV776ymlsMtGKj8g==}

@@ -1483,6 +1506,10 @@ packages:
    resolution: {integrity: sha512-PAJdDJusoxnwm1VwW07VWwUN1sl7smmC3OKggvndJFadxxDRyFJBX/ggnu/KE4kQAB7a3Dp8f/YXC1FlUprWmA==}
    engines: {node: '>= 16'}

+  chokidar@3.6.0:
+    resolution: {integrity: sha512-7VT13fmjotKpGipCW9JEQAusEPE+Ei8nl6/g4FBAmIm0GOOLMua9NDDo/DWp0ZAxCr3cPq5ZpBqmPAQgDda2Pw==}
+    engines: {node: '>= 8.10.0'}
+
  class-variance-authority@0.7.1:
    resolution: {integrity: sha512-Ka+9Trutv7G8M6WT6SeiRWz792K5qEqIGEGzXKhAE6xOWAY6pPH8U+9IY3oCMv6kqTmLsv7Xh/2w2RigkePMsg==}

@@ -1759,12 +1786,19 @@ packages:
  fast-deep-equal@3.1.3:
    resolution: {integrity: sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q==}

+  fast-glob@3.3.3:
+    resolution: {integrity: sha512-7MptL8U0cqcFdzIzwOTHoilX9x5BrNqye7Z/LuC7kCMRio1EMSyqRK3BEAUD7sXRq4iT4AzTVuZdhgQ2TCvYLg==}
+    engines: {node: '>=8.6.0'}
+
  fast-json-stable-stringify@2.1.0:
    resolution: {integrity: sha512-lhd/wF+Lk98HZoTCtlVraHtfh5XYijIjalXck7saUtuanSDyLMxnHhSXEDJqHxD7msR8D0uCmqlkwjCV8xvwHw==}

  fast-levenshtein@2.0.6:
    resolution: {integrity: sha512-DCXu6Ifhqcks7TZKY3Hxp3y6qphY5SJZmrWMDrKcERSOXWQdMhU9Ig/PYrzyw/ul9jOIyh0N4M0tbC5hodg8dw==}

+  fastq@1.20.1:
+    resolution: {integrity: sha512-GGToxJ/w1x32s/D2EKND7kTil4n8OVk/9mycTc4VDza13lOvpUZTGX3mFSCtV9ksdGBVzvsyAVLM6mHFThxXxw==}
+
  fdir@6.5.0:
    resolution: {integrity: sha512-tIbYtZbucOs0BRGqPJkshJUYdL+SDH7dVM8gjy+ERp3WAUjLEFJE+02kanyHtwjWOnwrKYBiwAmM0p4kLJAnXg==}
    engines: {node: '>=12.0.0'}
@@ -1797,6 +1831,10 @@ packages:
    resolution: {integrity: sha512-dKx12eRCVIzqCxFGplyFKJMPvLEWgmNtUrpTiJIR5u97zEhRG8ySrtboPHZXx7daLxQVrl643cTzbab2tkQjxg==}
    engines: {node: '>= 0.4'}

+  fs-extra@11.3.5:
+    resolution: {integrity: sha512-eKpRKAovdpZtR1WopLHxlBWvAgPny3c4gX1G5Jhwmmw4XJj0ifSD5qB5TOo8hmA0wlRKDAOAhEE1yVPgs6Fgcg==}
+    engines: {node: '>=14.14'}
+
  fsevents@2.3.3:
    resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==}
    engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0}
@@ -1839,6 +1877,10 @@ packages:
  get-tsconfig@4.14.0:
    resolution: {integrity: sha512-yTb+8DXzDREzgvYmh6s9vHsSVCHeC0G3PI5bEXNBHtmshPnO+S5O7qgLEOn0I5QvMy6kpZN8K1NKGyilLb93wA==}

+  glob-parent@5.1.2:
+    resolution: {integrity: sha512-AOIgSQCepiJYwP3ARnGx+5VnTu2HBYdzbGP45eLw1vr3zB3vZLeyed1sC9hnbcOc9/SrMyM5RPQrkGz4aS9Zow==}
+    engines: {node: '>= 6'}
+
  glob-parent@6.0.2:
    resolution: {integrity: sha512-XxwI8EOhVQgWp6iDL+3b0r86f4d6AX6zSU55HfB4ydCEuXLXc5FcYeOu+nnGftS4TEju/11rt4KJPTMgbfmv4A==}
    engines: {node: '>=10.13.0'}
@@ -1859,6 +1901,9 @@ packages:
    resolution: {integrity: sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==}
    engines: {node: '>= 0.4'}

+  graceful-fs@4.2.11:
+    resolution: {integrity: sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==}
+
  happy-dom@20.9.0:
    resolution: {integrity: sha512-GZZ9mKe8r646NUAf/zemnGbjYh4Bt8/MqASJY+pSm5ZDtc3YQox+4gsLI7yi1hba6o+eCsGxpHn5+iEVn31/FQ==}
    engines: {node: '>=20.0.0'}
@@ -1928,6 +1973,10 @@ packages:
    resolution: {integrity: sha512-n4ZT37wG78iz03xPRKJrHTdZbe3IicyucEtdRsV5yglwc3GyUfbAfpSeD0FJ41NbUNSt5wbhqfp1fS+BgnvDFQ==}
    engines: {node: '>= 0.4'}

+  is-binary-path@2.1.0:
+    resolution: {integrity: sha512-ZMERYes6pDydyuGidse7OsHxtbI7WVeUEozgR/g7rd0xUimYNlvZRE/K2MgZTjWy725IfelLeVcEM97mmtRGXw==}
+    engines: {node: '>=8'}
+
  is-boolean-object@1.2.2:
    resolution: {integrity: sha512-wa56o2/ElJMYqjCjGkXri7it5FbebW5usLw/nPmCMs5DeZ7eziSYZhSmPRn0txqeW4LnAmQQU7FgqLpsEFKM4A==}
    engines: {node: '>= 0.4'}
@@ -2058,6 +2107,9 @@ packages:
    engines: {node: '>=6'}
    hasBin: true

+  jsonfile@6.2.1:
+    resolution: {integrity: sha512-zwOTdL3rFQ/lRdBnntKVOX6k5cKJwEc1HdilT71BWEu7J41gXIB2MRp+vxduPSwZJPWBxEzv4yH1wYLJGUHX4Q==}
+
  jszip@3.10.1:
    resolution: {integrity: sha512-xXDvecyTpGLrqFrvkrUSoxxfJI5AH7U8zxxtVclpsUtMCq4JQ290LY8AW5c7Ggnr/Y/oK+bQMbqK2qmtk3pN4g==}

@@ -2107,10 +2159,18 @@ packages:
    resolution: {integrity: sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==}
    engines: {node: '>= 0.4'}

+  merge2@1.4.1:
+    resolution: {integrity: sha512-8q7VEgMJW4J8tcfVPy8g09NcQwZdbwFEqhe/WZkoIzjn/3TGDwtOCYtXGxA3O8tPzpczCCDgv+P2P5y00ZJOOg==}
+    engines: {node: '>= 8'}
+
  micromatch@4.0.7:
    resolution: {integrity: sha512-LPP/3KorzCwBxfeUuZmaR6bG2kdeHSbe0P2tY3FLRU4vYrjYz5hI4QZwV0njUx3jeuKe67YukQ1LSPZBKDqO/Q==}
    engines: {node: '>=8.6'}

+  micromatch@4.0.8:
+    resolution: {integrity: sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA==}
+    engines: {node: '>=8.6'}
+
  minimatch@10.2.5:
    resolution: {integrity: sha512-MULkVLfKGYDFYejP07QOurDLLQpcjk7Fw+7jXS2R2czRQzR56yHRveU5NDJEOviH+hETZKSkIk5c+T23GjFUMg==}
    engines: {node: 18 || 20 || >=22}
@@ -2145,6 +2205,10 @@ packages:
    resolution: {integrity: sha512-GYVXHE2KnrzAfsAjl4uP++evGFCrAU1jta4ubEjIG7YWt/64Gqv66a30yKwWczVjA6j3bM4nBwH7Pk1JmDHaxQ==}
    engines: {node: '>=18'}

+  normalize-path@3.0.0:
+    resolution: {integrity: sha512-6eZs5Ls3WtCisHWp9S2GUy8dqkpGi4BVSz3GaqiE6ezub0512ESztXUwUB6C6IKbQkY2Pnb/mD4WYojCRwcwLA==}
+    engines: {node: '>=0.10.0'}
+
  object-assign@4.1.1:
    resolution: {integrity: sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg==}
    engines: {node: '>=0.10.0'}
@@ -2193,6 +2257,10 @@ packages:
    resolution: {integrity: sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw==}
    engines: {node: '>=10'}

+  p-map@7.0.4:
+    resolution: {integrity: sha512-tkAQEw8ysMzmkhgw8k+1U/iPhWNhykKnSk4Rd5zLoPJCuJaGRPo6YposrZgaxHKzDHdDWWZvE/Sk7hsL2X/CpQ==}
+    engines: {node: '>=18'}
+
  pako@1.0.11:
    resolution: {integrity: sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw==}

@@ -2262,6 +2330,9 @@ packages:
    resolution: {integrity: sha512-vYt7UD1U9Wg6138shLtLOvdAu+8DsC/ilFtEVHcH+wydcSpNE20AfSOduf6MkRFahL5FY7X1oU7nKVZFtfq8Fg==}
    engines: {node: '>=6'}

+  queue-microtask@1.2.3:
+    resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==}
+
  re-resizable@6.11.2:
    resolution: {integrity: sha512-2xI2P3OHs5qw7K0Ud1aLILK6MQxW50TcO+DetD9eIV58j84TqYeHoZcL9H4GXFXXIh7afhH8mv5iUCXII7OW7A==}
    peerDependencies:
@@ -2339,6 +2410,10 @@ packages:
  readable-stream@2.3.8:
    resolution: {integrity: sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA==}

+  readdirp@3.6.0:
+    resolution: {integrity: sha512-hOS089on8RduqdbhvQ5Z37A0ESjsqz6qnRcffsMU3495FuTdqSm+7bhJ29JvIOsBDEEnan5DPu9t3To9VRlMzA==}
+    engines: {node: '>=8.10.0'}
+
  reflect.getprototypeof@1.0.10:
    resolution: {integrity: sha512-00o4I+DVrefhv+nX0ulyi3biSHCPDe+yLv5o/p6d/UVlirijB8E16FtfwSAi4g3tcqrQ4lRAqQSoFEZJehYEcw==}
    engines: {node: '>= 0.4'}
@@ -2364,11 +2439,18 @@ packages:
    engines: {node: '>= 0.4'}
    hasBin: true

+  reusify@1.1.0:
+    resolution: {integrity: sha512-g6QUff04oZpHs0eG5p83rFLhHeV00ug/Yf9nZM6fLeUrPguBTkTQOdpAWWspMh55TZfVQDPaN3NQJfbVRAxdIw==}
+    engines: {iojs: '>=1.0.0', node: '>=0.10.0'}
+
  rollup@4.60.4:
    resolution: {integrity: sha512-WHeFSbZYsPu3+bLoNRUuAO+wavNlocOPf3wSHTP7hcFKVnJeWsYlCDbr3mTS14FCizf9ccIxXA8sGL8zKeQN3g==}
    engines: {node: '>=18.0.0', npm: '>=8.0.0'}
    hasBin: true

+  run-parallel@1.2.0:
+    resolution: {integrity: sha512-5l4VyZR86LZ/lDxZTR6jqL8AFE2S0IFLMP26AbjsLVADxHdhB/c0GUsH+y39UfCi3dzz8OlQuPmnaJOMoDHQBA==}
+
  safe-array-concat@1.1.4:
    resolution: {integrity: sha512-wtZlHyOje6OZTGqAoaDKxFkgRtkF9CnHAVnCHKfuj200wAgL+bSJhdsCD2l0Qx/2ekEXjPWcyKkfGb5CPboslg==}
    engines: {node: '>=0.4'}
@@ -2572,6 +2654,10 @@ packages:
  undici-types@6.21.0:
    resolution: {integrity: sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ==}

+  universalify@2.0.1:
+    resolution: {integrity: sha512-gptHNQghINnc/vTGIk0SOFGFNXw7JVrlRUtConJRlvaw6DuX0wO5Jeko9sWrMBhh+PsYAZ7oXAiOnf/UKogyiw==}
+    engines: {node: '>= 10.0.0'}
+
  unrs-resolver@1.12.2:
    resolution: {integrity: sha512-dmlRxBJJayXjqTwC+JtF1HhJmgf3ftQ3YejFcZrf4+KKtJv0qDsK1pjqaaVjG7wJ5NJ6UVP1OqRMQ71Z4C3rxQ==}

@@ -2612,6 +2698,12 @@ packages:
    engines: {node: ^18.0.0 || >=20.0.0}
    hasBin: true

+  vite-plugin-static-copy@2.3.2:
+    resolution: {integrity: sha512-iwrrf+JupY4b9stBttRWzGHzZbeMjAHBhkrn67MNACXJVjEMRpCI10Q3AkxdBkl45IHaTfw/CNVevzQhP7yTwg==}
+    engines: {node: ^18.0.0 || >=20.0.0}
+    peerDependencies:
+      vite: ^5.0.0 || ^6.0.0
+
  vite@5.4.21:
    resolution: {integrity: sha512-o5a9xKjbtuhY6Bi5S3+HvbRERmouabWbyUcpXXUA1u+GNUKoROi9byOJ8M0nHbHYHkYICiMlqxkg1KkYmm25Sw==}
    engines: {node: ^18.0.0 || >=20.0.0}
@@ -3075,6 +3167,18 @@ snapshots:
      '@tybys/wasm-util': 0.10.2
    optional: true

+  '@nodelib/fs.scandir@2.1.5':
+    dependencies:
+      '@nodelib/fs.stat': 2.0.5
+      run-parallel: 1.2.0
+
+  '@nodelib/fs.stat@2.0.5': {}
+
+  '@nodelib/fs.walk@1.2.8':
+    dependencies:
+      '@nodelib/fs.scandir': 2.1.5
+      fastq: 1.20.1
+
  '@nolyfill/is-core-module@1.0.39': {}

  '@pdf-lib/standard-fonts@1.0.0':
@@ -3942,6 +4046,11 @@ snapshots:

  ansi-styles@5.2.0: {}

+  anymatch@3.1.3:
+    dependencies:
+      normalize-path: 3.0.0
+      picomatch: 2.3.2
+
  argparse@2.0.1: {}

  aria-hidden@1.2.6:
@@ -4016,6 +4125,8 @@ snapshots:

  baseline-browser-mapping@2.10.32: {}

+  binary-extensions@2.3.0: {}
+
  brace-expansion@1.1.14:
    dependencies:
      balanced-match: 1.0.2
@@ -4075,6 +4186,18 @@ snapshots:

  check-error@2.1.3: {}

+  chokidar@3.6.0:
+    dependencies:
+      anymatch: 3.1.3
+      braces: 3.0.3
+      glob-parent: 5.1.2
+      is-binary-path: 2.1.0
+      is-glob: 4.0.3
+      normalize-path: 3.0.0
+      readdirp: 3.6.0
+    optionalDependencies:
+      fsevents: 2.3.3
+
  class-variance-authority@0.7.1:
    dependencies:
      clsx: 2.1.1
@@ -4448,10 +4571,22 @@ snapshots:

  fast-deep-equal@3.1.3: {}

+  fast-glob@3.3.3:
+    dependencies:
+      '@nodelib/fs.stat': 2.0.5
+      '@nodelib/fs.walk': 1.2.8
+      glob-parent: 5.1.2
+      merge2: 1.4.1
+      micromatch: 4.0.8
+
  fast-json-stable-stringify@2.1.0: {}

  fast-levenshtein@2.0.6: {}

+  fastq@1.20.1:
+    dependencies:
+      reusify: 1.1.0
+
  fdir@6.5.0(picomatch@4.0.4):
    optionalDependencies:
      picomatch: 4.0.4
@@ -4480,6 +4615,12 @@ snapshots:
    dependencies:
      is-callable: 1.2.7

+  fs-extra@11.3.5:
+    dependencies:
+      graceful-fs: 4.2.11
+      jsonfile: 6.2.1
+      universalify: 2.0.1
+
  fsevents@2.3.3:
    optional: true

@@ -4530,6 +4671,10 @@ snapshots:
    dependencies:
      resolve-pkg-maps: 1.0.0

+  glob-parent@5.1.2:
+    dependencies:
+      is-glob: 4.0.3
+
  glob-parent@6.0.2:
    dependencies:
      is-glob: 4.0.3
@@ -4545,6 +4690,8 @@ snapshots:

  gopd@1.2.0: {}

+  graceful-fs@4.2.11: {}
+
  happy-dom@20.9.0:
    dependencies:
      '@types/node': 20.19.41
@@ -4618,6 +4765,10 @@ snapshots:
    dependencies:
      has-bigints: 1.1.0

+  is-binary-path@2.1.0:
+    dependencies:
+      binary-extensions: 2.3.0
+
  is-boolean-object@1.2.2:
    dependencies:
      call-bound: 1.0.4
@@ -4738,6 +4889,12 @@ snapshots:

  json5@2.2.3: {}

+  jsonfile@6.2.1:
+    dependencies:
+      universalify: 2.0.1
+    optionalDependencies:
+      graceful-fs: 4.2.11
+
  jszip@3.10.1:
    dependencies:
      lie: 3.3.0
@@ -4788,11 +4945,18 @@ snapshots:

  math-intrinsics@1.1.0: {}

+  merge2@1.4.1: {}
+
  micromatch@4.0.7:
    dependencies:
      braces: 3.0.3
      picomatch: 2.3.2

+  micromatch@4.0.8:
+    dependencies:
+      braces: 3.0.3
+      picomatch: 2.3.2
+
  minimatch@10.2.5:
    dependencies:
      brace-expansion: 5.0.6
@@ -4820,6 +4984,8 @@ snapshots:

  node-releases@2.0.46: {}

+  normalize-path@3.0.0: {}
+
  object-assign@4.1.1: {}

  object-inspect@1.13.4: {}
@@ -4885,6 +5051,8 @@ snapshots:
    dependencies:
      p-limit: 3.1.0

+  p-map@7.0.4: {}
+
  pako@1.0.11: {}

  parent-module@1.0.1:
@@ -4944,6 +5112,8 @@ snapshots:

  punycode@2.3.1: {}

+  queue-microtask@1.2.3: {}
+
  re-resizable@6.11.2(react-dom@18.3.1(react@18.3.1))(react@18.3.1):
    dependencies:
      react: 18.3.1
@@ -5045,6 +5215,10 @@ snapshots:
      string_decoder: 1.1.1
      util-deprecate: 1.0.2

+  readdirp@3.6.0:
+    dependencies:
+      picomatch: 2.3.2
+
  reflect.getprototypeof@1.0.10:
    dependencies:
      call-bind: 1.0.9
@@ -5085,6 +5259,8 @@ snapshots:
      path-parse: 1.0.7
      supports-preserve-symlinks-flag: 1.0.0

+  reusify@1.1.0: {}
+
  rollup@4.60.4:
    dependencies:
      '@types/estree': 1.0.8
@@ -5116,6 +5292,10 @@ snapshots:
      '@rollup/rollup-win32-x64-msvc': 4.60.4
      fsevents: 2.3.3

+  run-parallel@1.2.0:
+    dependencies:
+      queue-microtask: 1.2.3
+
  safe-array-concat@1.1.4:
    dependencies:
      call-bind: 1.0.9
@@ -5352,6 +5532,8 @@ snapshots:

  undici-types@6.21.0: {}

+  universalify@2.0.1: {}
+
  unrs-resolver@1.12.2:
    dependencies:
      napi-postinstall: 0.3.4
@@ -5424,6 +5606,15 @@ snapshots:
      - supports-color
      - terser

+  vite-plugin-static-copy@2.3.2(vite@5.4.21(@types/node@20.19.41)):
+    dependencies:
+      chokidar: 3.6.0
+      fast-glob: 3.3.3
+      fs-extra: 11.3.5
+      p-map: 7.0.4
+      picocolors: 1.1.1
+      vite: 5.4.21(@types/node@20.19.41)
+
  vite@5.4.21(@types/node@20.19.41):
    dependencies:
      esbuild: 0.21.5
--- a/src/anchor/pdf-viewer-adapter-spike.tsx
+++ b/src/anchor/pdf-viewer-adapter-spike.tsx
@@ -298,7 +298,20 @@ export function PdfSpikeViewer(props: PdfSpikeViewerProps) {
      className={wrapperClasses.length > 0 ? wrapperClasses : undefined}
      style={{ height: "100%" }}
    >
-      <PdfLoader document={pdfUrl}>
+      <PdfLoader
+        document={{
+          url: pdfUrl,
+          // Without these two, PDFs with CID fonts (most CJK + many
+          // European court documents) or unembedded standard fonts get
+          // rendered with substitute metrics, which shifts every
+          // text-layer span out of alignment with the canvas glyphs.
+          // vite.config.ts copies both directories from pdfjs-dist into
+          // the served root.
+          cMapUrl: "/cmaps/",
+          cMapPacked: true,
+          standardFontDataUrl: "/standard_fonts/",
+        }}
+      >
        {(pdfDocument) => (
          <PdfHighlighter
            pdfDocument={pdfDocument}
--- a/vite.config.ts
+++ b/vite.config.ts
@@ -1,12 +1,34 @@
 import { defineConfig } from "vite";
 import react from "@vitejs/plugin-react";
+import { viteStaticCopy } from "vite-plugin-static-copy";
 import { fileURLToPath } from "node:url";
 import { dirname, resolve } from "node:path";

 const __dirname = dirname(fileURLToPath(import.meta.url));

 export default defineConfig({
-  plugins: [react()],
+  plugins: [
+    react(),
+    // PDF.js needs its cmaps (character maps for CID fonts) and
+    // standard fonts (Helvetica/Times/Courier metrics) to position
+    // text-layer spans correctly. Without them, PDFs with embedded
+    // CID fonts or unembedded standard fonts get rendered to canvas
+    // OK but their textLayer overlays land in the wrong place — text
+    // appears unselectable or selection jumps to a different region.
+    // We serve both directories straight from `node_modules/pdfjs-dist`.
+    viteStaticCopy({
+      targets: [
+        {
+          src: resolve(__dirname, "node_modules/pdfjs-dist/cmaps") + "/[!.]*",
+          dest: "cmaps",
+        },
+        {
+          src: resolve(__dirname, "node_modules/pdfjs-dist/standard_fonts") + "/[!.]*",
+          dest: "standard_fonts",
+        },
+      ],
+    }),
+  ],
  resolve: {
    alias: {
      "@shared": resolve(__dirname, "src/shared"),