Add PGS to SRT OCR subtitle extraction feature

Implements OCR-based conversion of PGS (Presentation Graphic Stream)
subtitles to SRT format with automatic tool detection.

Features:
- Auto-detect Tesseract OCR from PATH or Subtitle Edit installations
- Auto-detect MKVToolNix from standard install locations
- Support multiple language codes (ISO 639-2/3, language names)
- GUI checkbox to enable/disable OCR for PGS subtitles
- Automatic cleanup of intermediate .sup files after conversion

Dependencies:
- pgsrip: PGS subtitle OCR engine
- pytesseract: Tesseract OCR wrapper
- babelfish: Language code handling
- opencv-python, cleanit, trakit: Image/metadata processing

Known limitation:
This feature works when running from source (python -m fastflix) but
not in PyInstaller-built executables due to subprocess environment
issues with pgsrip. Users needing PGS OCR should run from source.

Author: mikeSGman

FastFlix_Windows_Installer.spec

@@ -1,5 +1,5 @@
 # -*- mode: python ; coding: utf-8 -*-
-from PyInstaller.utils.hooks import collect_submodules
+from PyInstaller.utils.hooks import collect_submodules, copy_metadata, collect_data_files
 import toml
 
 block_cipher = None
@@ -24,9 +24,12 @@ all_imports.remove("python-box")
 all_imports.append("box")
 all_imports.append("iso639")
 
+# Add pgsrip for OCR support
+all_imports.extend(["pgsrip", "pytesseract", "cv2", "numpy", "pysrt", "babelfish", "babelfish.converters", "babelfish.converters.alpha2", "babelfish.converters.alpha3b", "babelfish.converters.alpha3t", "babelfish.converters.name", "babelfish.converters.opensubtitles", "cleanit"])
+
 a = Analysis(['fastflix\\__main__.py'],
              binaries=[],
-             datas=[('CHANGES', 'fastflix\\.'), ('docs\\build-licenses.txt', 'docs')] + all_fastflix_files,
+             datas=[('CHANGES', 'fastflix\\.'), ('docs\\build-licenses.txt', 'docs')] + all_fastflix_files + copy_metadata('pgsrip') + copy_metadata('pytesseract') + copy_metadata('babelfish') + copy_metadata('cleanit') + copy_metadata('trakit') + collect_data_files('babelfish') + collect_data_files('cleanit'),
              hiddenimports=all_imports,
              hookspath=[],
              runtime_hooks=[],

FastFlix_Windows_OneFile.spec

@@ -2,7 +2,7 @@
 import os
 import toml
 
-from PyInstaller.utils.hooks import collect_submodules
+from PyInstaller.utils.hooks import collect_submodules, copy_metadata, collect_data_files
 
 block_cipher = None
 
@@ -27,13 +27,16 @@ all_imports.remove("python-box")
 all_imports.append("box")
 all_imports.append("iso639")
 
+# Add pgsrip for OCR support
+all_imports.extend(["pgsrip", "pytesseract", "cv2", "numpy", "pysrt", "babelfish", "babelfish.converters", "babelfish.converters.alpha2", "babelfish.converters.alpha3b", "babelfish.converters.alpha3t", "babelfish.converters.name", "babelfish.converters.opensubtitles", "cleanit"])
+
 portable_file = "fastflix\\portable.py"
 with open(portable_file, "w") as portable:
     portable.write(" ")
 
 a = Analysis(['fastflix\\__main__.py'],
              binaries=[],
-             datas=[('CHANGES', 'fastflix\\.'), ('docs\\build-licenses.txt', 'docs')] + all_fastflix_files,
+             datas=[('CHANGES', 'fastflix\\.'), ('docs\\build-licenses.txt', 'docs')] + all_fastflix_files + copy_metadata('pgsrip') + copy_metadata('pytesseract') + copy_metadata('babelfish') + copy_metadata('cleanit') + copy_metadata('trakit') + collect_data_files('babelfish') + collect_data_files('cleanit'),
              hiddenimports=all_imports,
              hookspath=[],
              runtime_hooks=[],

README.md

@@ -87,6 +87,25 @@ Windows: Go into FastFlix's settings and select the corresponding EXE file for e
 
 Linux: Install the rpm or deb and restart FastFlix
 
+# Subtitle Extraction
+
+FastFlix can extract subtitles from video files in various formats including SRT, ASS, SSA, and PGS.
+
+## PGS to SRT OCR Conversion
+
+FastFlix includes experimental support for converting PGS (Presentation Graphic Stream) subtitles to SRT format using OCR. This feature automatically detects and uses installed OCR tools.
+
+**Requirements (auto-detected)**:
+- Tesseract OCR 4.x or higher
+- MKVToolNix (mkvextract/mkvmerge)
+
+**Important**: This feature only works when running FastFlix from source:
+```bash
+python -m fastflix
+```
+
+The Windows/Mac executable builds do not support PGS OCR due to environment limitations with the pgsrip library. If you need this feature, install FastFlix via pip and run from source.
+
 # HDR
 
 On any 10-bit or higher video output, FastFlix will copy the input HDR colorspace (bt2020). Which is [different than HDR10 or HDR10+](https://codecalamity.com/hdr-hdr10-hdr10-hlg-and-dolby-vision/).

WINDOWS_BUILD.md

@@ -0,0 +1,133 @@
+# Building FastFlix on Windows
+
+This guide explains how to build FastFlix executables on Windows.
+
+## Prerequisites
+
+1. **Python 3.12 or higher**
+   - Download from [python.org](https://www.python.org/downloads/)
+   - Make sure to check "Add Python to PATH" during installation
+
+2. **Git** (to clone/update the repository)
+   - Download from [git-scm.com](https://git-scm.com/download/win)
+
+## Build Steps
+
+### 1. Open Command Prompt or PowerShell
+
+Navigate to where you want to clone/have the FastFlix repository:
+
+```bash
+cd C:\path\to\your\projects
+git clone https://github.com/cdgriffith/FastFlix.git
+cd FastFlix
+```
+
+Or if you already have it:
+
+```bash
+cd C:\path\to\FastFlix
+```
+
+### 2. Create and Activate Virtual Environment
+
+```bash
+python -m venv venv
+venv\Scripts\activate
+```
+
+You should see `(venv)` in your command prompt.
+
+### 3. Install Dependencies
+
+```bash
+pip install --upgrade pip
+pip install -e ".[dev]"
+```
+
+This installs FastFlix in editable mode with all development dependencies including PyInstaller.
+
+### 4. Build the Executable
+
+You have two options:
+
+#### Option A: Single Executable (Recommended for distribution)
+
+```bash
+pyinstaller FastFlix_Windows_OneFile.spec
+```
+
+The executable will be in: `dist\FastFlix.exe`
+
+#### Option B: Directory with Multiple Files (Faster startup)
+
+```bash
+pyinstaller FastFlix_Windows_Installer.spec
+```
+
+The executable will be in: `dist\FastFlix\FastFlix.exe`
+
+### 5. Test the Build
+
+```bash
+cd dist
+FastFlix.exe
+```
+
+Or for the installer version:
+
+```bash
+cd dist\FastFlix
+FastFlix.exe
+```
+
+## Running Without Building (For Testing)
+
+If you just want to test changes without building an executable:
+
+```bash
+python -m fastflix
+```
+
+## Troubleshooting
+
+### Missing Dependencies
+
+If you get import errors, try reinstalling:
+
+```bash
+pip install --upgrade --force-reinstall -e ".[dev]"
+```
+
+### Build Errors
+
+1. Make sure you're in the FastFlix root directory
+2. Ensure the virtual environment is activated (you see `(venv)`)
+3. Try deleting `build` and `dist` folders and rebuilding:
+
+```bash
+rmdir /s /q build dist
+pyinstaller FastFlix_Windows_OneFile.spec
+```
+
+### FFmpeg Not Found
+
+The FastFlix executable doesn't include FFmpeg. You need to:
+
+1. Download FFmpeg from [ffmpeg.org](https://ffmpeg.org/download.html#build-windows)
+2. Extract it somewhere
+3. Add the `bin` folder to your PATH, or configure it in FastFlix settings
+
+## Known Limitations
+
+### PGS to SRT OCR (PyInstaller builds)
+
+Due to an upstream issue in pgsrip v0.1.12, PGS to SRT OCR conversion does not work in PyInstaller-built executables. The feature works perfectly when running from source (`python -m fastflix`).
+
+If you need PGS OCR functionality, please run FastFlix from source instead of using the compiled executable.
+
+## Notes
+
+- The build process creates a `portable.py` file temporarily (it's removed after)
+- The `.spec` files automatically collect all dependencies from `pyproject.toml`
+- The icon is located at `fastflix\data\icon.ico`

fastflix/__main__.py

@@ -1,11 +1,35 @@
 # -*- coding: utf-8 -*-
+import os
 import sys
 import traceback
 from multiprocessing import freeze_support
+from pathlib import Path
 
 from fastflix.entry import main
 
 
+def setup_ocr_environment():
+    """Set up environment variables for OCR tools early in app startup.
+
+    This is necessary for PyInstaller frozen executables where os.environ
+    modifications later in the code don't properly propagate to subprocesses.
+    """
+    from fastflix.models.config import find_ocr_tool
+
+    # Find tesseract and add to PATH
+    tesseract_path = find_ocr_tool("tesseract")
+    if tesseract_path:
+        tesseract_dir = str(Path(tesseract_path).parent)
+        os.environ["PATH"] = f"{tesseract_dir}{os.pathsep}{os.environ.get('PATH', '')}"
+        os.environ["TESSERACT_CMD"] = str(tesseract_path)
+
+    # Find mkvmerge and add MKVToolNix to PATH
+    mkvmerge_path = find_ocr_tool("mkvmerge")
+    if mkvmerge_path:
+        mkvtoolnix_dir = str(Path(mkvmerge_path).parent)
+        os.environ["PATH"] = f"{mkvtoolnix_dir}{os.pathsep}{os.environ.get('PATH', '')}"
+
+
 def start_fastflix():
     exit_code = 2
     portable_mode = True
@@ -17,6 +41,9 @@ def start_fastflix():
     if portable_mode:
         print("PORTABLE MODE DETECTED: now using local config file and workspace in same directory as the executable")
 
+    # Set up OCR environment variables early for PyInstaller compatibility
+    setup_ocr_environment()
+
     try:
         exit_code = main(portable_mode)
     except Exception:

fastflix/models/config.py

@@ -99,6 +99,115 @@ def where(filename: str, portable_mode=False) -> Path | None:
     return None
 
 
+def find_ocr_tool(name):
+    """Find OCR tools (tesseract, mkvmerge, pgsrip) similar to how we find FFmpeg"""
+    # Check environment variable
+    if ocr_location := os.getenv(f"FF_{name.upper()}"):
+        return Path(ocr_location).absolute()
+
+    # Check system PATH
+    if (ocr_location := shutil.which(name)) is not None:
+        return Path(ocr_location).absolute()
+
+    # Special handling for tesseract on Windows (not in PATH by default)
+    if name == "tesseract" and win_based:
+        # Check common install locations using environment variables
+        localappdata = os.getenv("LOCALAPPDATA")
+        appdata = os.getenv("APPDATA")
+        program_files = os.getenv("PROGRAMFILES")
+        program_files_x86 = os.getenv("PROGRAMFILES(X86)")
+
+        # Check for Subtitle Edit's Tesseract installations and find the newest version
+        subtitle_edit_versions = []
+        if appdata:
+            subtitle_edit_dir = Path(appdata) / "Subtitle Edit"
+            if subtitle_edit_dir.exists():
+                # Find all Tesseract* directories
+                for tesseract_dir in subtitle_edit_dir.glob("Tesseract*"):
+                    tesseract_exe = tesseract_dir / "tesseract.exe"
+                    if tesseract_exe.exists():
+                        # Extract version number from directory name (e.g., Tesseract550 -> 550)
+                        version_str = tesseract_dir.name.replace("Tesseract", "")
+                        try:
+                            version = int(version_str)
+                            subtitle_edit_versions.append((version, tesseract_exe))
+                        except ValueError:
+                            # If we can't parse version, still add it with version 0
+                            subtitle_edit_versions.append((0, tesseract_exe))
+
+        # If we found Subtitle Edit versions, return the newest one
+        if subtitle_edit_versions:
+            subtitle_edit_versions.sort(reverse=True)  # Sort by version descending
+            return subtitle_edit_versions[0][1]
+
+        common_paths = []
+        # Check user-local installation first
+        if localappdata:
+            common_paths.append(Path(localappdata) / "Programs" / "Tesseract-OCR" / "tesseract.exe")
+        # Check system-wide installations
+        if program_files:
+            common_paths.append(Path(program_files) / "Tesseract-OCR" / "tesseract.exe")
+        if program_files_x86:
+            common_paths.append(Path(program_files_x86) / "Tesseract-OCR" / "tesseract.exe")
+
+        for path in common_paths:
+            if path.exists():
+                return path
+
+        # Check Windows registry for Tesseract install location
+        try:
+            import winreg
+
+            # Try HKEY_LOCAL_MACHINE first (system-wide install)
+            for root_key in [winreg.HKEY_LOCAL_MACHINE, winreg.HKEY_CURRENT_USER]:
+                try:
+                    key = winreg.OpenKey(root_key, r"SOFTWARE\Tesseract-OCR")
+                    install_path = winreg.QueryValueEx(key, "InstallDir")[0]
+                    winreg.CloseKey(key)
+                    tesseract_exe = Path(install_path) / "tesseract.exe"
+                    if tesseract_exe.exists():
+                        return tesseract_exe
+                except (FileNotFoundError, OSError):
+                    pass
+        except ImportError:
+            pass
+
+    # Special handling for mkvmerge on Windows
+    if name == "mkvmerge" and win_based:
+        # Check common install locations using environment variables
+        localappdata = os.getenv("LOCALAPPDATA")
+        program_files = os.getenv("PROGRAMFILES")
+        program_files_x86 = os.getenv("PROGRAMFILES(X86)")
+
+        common_paths = []
+        # Check user-local installation first
+        if localappdata:
+            common_paths.append(Path(localappdata) / "Programs" / "MKVToolNix" / "mkvmerge.exe")
+        # Check system-wide installations
+        if program_files:
+            common_paths.append(Path(program_files) / "MKVToolNix" / "mkvmerge.exe")
+        if program_files_x86:
+            common_paths.append(Path(program_files_x86) / "MKVToolNix" / "mkvmerge.exe")
+
+        for path in common_paths:
+            if path.exists():
+                return path
+
+    # Check in FastFlix OCR tools folder
+    ocr_folder = Path(user_data_dir("FastFlix_OCR", appauthor=False, roaming=True))
+    if ocr_folder.exists():
+        for file in ocr_folder.iterdir():
+            if file.is_file() and file.name.lower() in (name, f"{name}.exe"):
+                return file
+        # Check bin subfolder
+        if (ocr_folder / "bin").exists():
+            for file in (ocr_folder / "bin").iterdir():
+                if file.is_file() and file.name.lower() in (name, f"{name}.exe"):
+                    return file
+
+    return None
+
+
 class Config(BaseModel):
     version: str = __version__
     config_path: Path = Field(default_factory=get_config)
@@ -168,6 +277,12 @@ class Config(BaseModel):
 
     disable_cover_extraction: bool = False
 
+    # PGS to SRT OCR Settings
+    enable_pgs_ocr: bool = False
+    tesseract_path: Path | None = Field(default_factory=lambda: find_ocr_tool("tesseract"))
+    mkvmerge_path: Path | None = Field(default_factory=lambda: find_ocr_tool("mkvmerge"))
+    pgs_ocr_language: str = "eng"
+
     def encoder_opt(self, profile_name, profile_option_name):
         encoder_settings = getattr(self.profiles[self.selected_profile], profile_name)
         if encoder_settings: