ocr: bundle Tesseract into release for click-and-run OCR

Make the standalone exe work with OCR out of the box — no separate
Tesseract install, no tesserocr DLL hell. Verified end-to-end: built the
exe, ran it frozen with the system Tesseract blinded, confirmed it
resolves the bundled binary and reads text ("CHAM RUNE").

- ocr.py: resolve an _APP_BASE (exe dir when frozen, else cwd) and prefer
  a bundled <exe_dir>/tesseract/tesseract.exe over PATH / Program Files.
  Resolve assets/tessdata to an absolute path so OCR no longer depends on
  the current working dir. Applies to both the tesserocr and pytesseract
  paths.
- build.py: copy a portable Tesseract (exe + DLLs) from TESSERACT_DIR
  (default C:\Program Files\Tesseract-OCR) into <release>/tesseract/. Our
  trained models in assets/tessdata are used via --tessdata-dir, so their
  tessdata is skipped. Warns (non-fatal) if Tesseract isn't present.
- ci.yml: choco install tesseract before the build so the bundle is
  reproducible on the runner; verify it landed in the release dir.
- test/conftest.py: apply the SSL cert-store workaround so pytest can be
  collected on Windows boxes with a corrupted cert store (no-op on CI).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.github/workflows/ci.yml

@@ -79,6 +79,15 @@ jobs:
           environment-file: environment-win11.yml
           use-only-tar-bz2: false
 
+      - name: Install Tesseract (bundled into the release for click-and-run OCR)
+        shell: powershell
+        run: |
+          $ErrorActionPreference = "Stop"
+          choco install tesseract --no-progress -y
+          if (-not (Test-Path "C:\Program Files\Tesseract-OCR\tesseract.exe")) {
+            throw "Tesseract install did not produce tesseract.exe"
+          }
+
       - name: Build exe
         shell: powershell
         env:
@@ -88,6 +97,15 @@ jobs:
           C:\Miniconda\condabin\conda.bat activate botty
           python build.py --conda_path C:\Miniconda
 
+      - name: Verify Tesseract was bundled
+        shell: powershell
+        run: |
+          $ErrorActionPreference = "Stop"
+          $BOTTY_DIR = Get-ChildItem -Directory -Name | Where-Object { $_ -match '^botty_v' } | Select-Object -First 1
+          $tess = Join-Path $BOTTY_DIR "tesseract\tesseract.exe"
+          if (-not (Test-Path $tess)) { throw "Tesseract was not bundled into $BOTTY_DIR" }
+          Write-Host "Bundled: $tess"
+
       - name: Launch smoke test (built executables)
         shell: powershell
         run: |

build.py

@@ -115,6 +115,26 @@ if __name__ == "__main__":
     shutil.copy("run.bat", f"{botty_dir}/")
     if os.path.exists("dependencies"):
         shutil.copytree("dependencies", f"{botty_dir}/dependencies")
+
+    # Bundle a portable Tesseract so the standalone exe is click-and-run with
+    # working OCR and no separate install. ocr.py prefers <exe_dir>/tesseract/
+    # tesseract.exe. Source: TESSERACT_DIR env or the default UB Mannheim path.
+    # Skipped (with a warning) if not present — the bot still works once the
+    # user runs install.bat, which sets OCR up the conda way.
+    tesseract_src = os.environ.get("TESSERACT_DIR", r"C:\Program Files\Tesseract-OCR")
+    tess_exe = os.path.join(tesseract_src, "tesseract.exe")
+    if os.path.isfile(tess_exe):
+        print(f"Bundling Tesseract from {tesseract_src}")
+        # Copy the exe + DLLs; skip their tessdata (we ship our own trained
+        # models in assets/tessdata and pass --tessdata-dir to point at them).
+        os.makedirs(f"{botty_dir}/tesseract", exist_ok=True)
+        for entry in os.listdir(tesseract_src):
+            src = os.path.join(tesseract_src, entry)
+            if os.path.isfile(src) and entry.lower().endswith((".exe", ".dll")):
+                shutil.copy(src, f"{botty_dir}/tesseract/")
+    else:
+        print(f"WARNING: Tesseract not found at {tesseract_src} — release will "
+              f"rely on install.bat for OCR setup. Set TESSERACT_DIR to bundle it.")
     clean_up()
 
     if args.random_name:

src/d2r_image/ocr.py

@@ -1,5 +1,24 @@
 import os
 import sys
+
+# Application base dir: the folder the exe lives in when frozen (PyInstaller),
+# otherwise the current working dir (repo root when running `python src/main.py`).
+# Used to locate the bundled tesseract + assets/tessdata regardless of cwd.
+if getattr(sys, "frozen", False):
+    _APP_BASE = os.path.dirname(sys.executable)
+else:
+    _APP_BASE = os.getcwd()
+
+
+def _resolve_under_base(rel_path: str) -> str:
+    """Return an absolute path to rel_path under the app base, else rel_path as-is."""
+    candidate = os.path.join(_APP_BASE, rel_path)
+    return candidate if os.path.exists(candidate) else rel_path
+
+
+# Absolute tessdata dir so OCR works no matter what the current working dir is.
+TESSDATA_DIR = _resolve_under_base("assets/tessdata")
+
 if os.name == 'nt':
     # Register conda DLL dirs so Python's .pyd loader (LOAD_LIBRARY_SEARCH_USER_DIRS)
     # can find tesserocr's dependencies (tesseract, leptonica, etc.)
@@ -18,12 +37,18 @@ except Exception:
 try:
     import pytesseract
     # pytesseract only looks for plain "tesseract" on PATH; it does not read
-    # PYTESSERACT_TESSERACT_CMD (set by run_botty.bat), so apply it here.
+    # PYTESSERACT_TESSERACT_CMD (set by run_botty.bat), so resolve the binary
+    # here. Search order prefers the tesseract bundled in the release (so the
+    # standalone exe is click-and-run with no separate tesseract install).
     import shutil
-    _cmd = os.environ.get("PYTESSERACT_TESSERACT_CMD")
-    if not (_cmd and os.path.isfile(_cmd)):
-        _cmd = shutil.which("tesseract") or r"C:\Program Files\Tesseract-OCR\tesseract.exe"
-    if os.path.isfile(_cmd):
+    _candidates = [
+        os.environ.get("PYTESSERACT_TESSERACT_CMD"),
+        os.path.join(_APP_BASE, "tesseract", "tesseract.exe"),  # bundled in release
+        shutil.which("tesseract"),
+        r"C:\Program Files\Tesseract-OCR\tesseract.exe",
+    ]
+    _cmd = next((c for c in _candidates if c and os.path.isfile(c)), None)
+    if _cmd:
         pytesseract.pytesseract.tesseract_cmd = _cmd
     else:
         pytesseract = None
@@ -89,8 +114,8 @@ def image_to_text(
             check_known_errors=check_known_errors, correct_words=correct_words
         )
 
-    with PyTessBaseAPI(psm=psm, oem=OEM.LSTM_ONLY, path=f"assets/tessdata", lang=model ) as api:
-        api.ReadConfigFile("assets/tessdata/ocr_config.txt")
+    with PyTessBaseAPI(psm=psm, oem=OEM.LSTM_ONLY, path=TESSDATA_DIR, lang=model ) as api:
+        api.ReadConfigFile(os.path.join(TESSDATA_DIR, "ocr_config.txt"))
         if word_list:
             api.SetVariable("user_words_file", word_list)
         #api.SetSourceResolution(72 * scale)
@@ -172,7 +197,7 @@ def _image_to_text_pytesseract(
     if digits_only:
         custom_config += " -c tessedit_char_whitelist=0123456789"
 
-    tessdata_dir = "assets/tessdata"
+    tessdata_dir = TESSDATA_DIR
 
     results = []
     for image in images:

test/conftest.py

@@ -0,0 +1,23 @@
+# Apply the same SSL cert-store workaround the bot entry points use, so the
+# test suite can be collected on Windows machines whose cert store is corrupted.
+# Importing the bot code pulls in discord/aiohttp, which calls
+# ssl.create_default_context() at import time; a malformed Windows cert raises
+# ssl.SSLError: [ASN1: NOT_ENOUGH_DATA]. No-op on a healthy cert store (incl. CI).
+import sys
+
+if sys.platform == "win32":
+    import ssl
+
+    _orig_load_default_certs = ssl.SSLContext.load_default_certs
+
+    def _safe_load_default_certs(self, purpose=ssl.Purpose.CLIENT_AUTH):
+        try:
+            _orig_load_default_certs(self, purpose)
+        except ssl.SSLError:
+            try:
+                import certifi
+                self.load_verify_locations(certifi.where())
+            except Exception:
+                pass
+
+    ssl.SSLContext.load_default_certs = _safe_load_default_certs