chore: backup before code cleanup

Backup commit before executing remove-unused-code proposal.
This includes all pending changes and new features.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/schemas/task.py

@@ -65,6 +65,139 @@ class PreprocessingContrastEnum(str, Enum):
     DOCUMENT = "document"
 
 
+class OCRPresetEnum(str, Enum):
+    """OCR processing preset for different document types.
+
+    Presets provide optimized PP-Structure configurations for common document types:
+    - TEXT_HEAVY: Reports, articles, manuals (disable table recognition)
+    - DATASHEET: Technical datasheets, TDS (conservative table parsing)
+    - TABLE_HEAVY: Financial reports, spreadsheets (full table recognition)
+    - FORM: Applications, surveys (conservative table parsing)
+    - MIXED: General documents (classification only)
+    - CUSTOM: User-defined settings (use ocr_config)
+    """
+    TEXT_HEAVY = "text_heavy"       # Reports, articles, manuals
+    DATASHEET = "datasheet"         # Technical datasheets, TDS
+    TABLE_HEAVY = "table_heavy"     # Financial reports, spreadsheets
+    FORM = "form"                   # Applications, surveys
+    MIXED = "mixed"                 # General documents
+    CUSTOM = "custom"               # User-defined settings
+
+
+class TableParsingModeEnum(str, Enum):
+    """Table parsing mode controlling how aggressively tables are parsed.
+
+    - FULL: Full table recognition with cell segmentation (aggressive)
+    - CONSERVATIVE: Disable wireless tables to prevent cell explosion
+    - CLASSIFICATION_ONLY: Only classify table regions, no cell segmentation
+    - DISABLED: Completely disable table recognition
+    """
+    FULL = "full"
+    CONSERVATIVE = "conservative"
+    CLASSIFICATION_ONLY = "classification_only"
+    DISABLED = "disabled"
+
+
+class OCRConfig(BaseModel):
+    """OCR processing configuration for PP-Structure.
+
+    Allows fine-grained control over PP-Structure parameters.
+    Use with ocr_preset=CUSTOM or to override specific preset values.
+    """
+    # Table Processing
+    table_parsing_mode: TableParsingModeEnum = Field(
+        default=TableParsingModeEnum.CONSERVATIVE,
+        description="Table parsing mode: full, conservative, classification_only, disabled"
+    )
+    enable_wired_table: bool = Field(
+        default=True,
+        description="Enable wired (bordered) table detection"
+    )
+    enable_wireless_table: bool = Field(
+        default=False,
+        description="Enable wireless (borderless) table detection. Can cause cell explosion."
+    )
+
+    # Layout Detection
+    layout_threshold: Optional[float] = Field(
+        default=None,
+        ge=0.0,
+        le=1.0,
+        description="Layout detection threshold. Higher = stricter. None uses default."
+    )
+    layout_nms_threshold: Optional[float] = Field(
+        default=None,
+        ge=0.0,
+        le=1.0,
+        description="Layout NMS threshold. None uses default."
+    )
+
+    # Preprocessing
+    use_doc_orientation_classify: bool = Field(
+        default=True,
+        description="Auto-detect and correct document rotation"
+    )
+    use_doc_unwarping: bool = Field(
+        default=False,
+        description="Correct document warping. Can cause distortion."
+    )
+    use_textline_orientation: bool = Field(
+        default=True,
+        description="Detect textline orientation"
+    )
+
+    # Recognition Modules
+    enable_chart_recognition: bool = Field(
+        default=True,
+        description="Enable chart/diagram recognition"
+    )
+    enable_formula_recognition: bool = Field(
+        default=True,
+        description="Enable math formula recognition"
+    )
+    enable_seal_recognition: bool = Field(
+        default=False,
+        description="Enable seal/stamp recognition"
+    )
+    enable_region_detection: bool = Field(
+        default=True,
+        description="Enable region detection for better structure"
+    )
+
+
+# Preset configurations mapping
+OCR_PRESET_CONFIGS = {
+    OCRPresetEnum.TEXT_HEAVY: OCRConfig(
+        table_parsing_mode=TableParsingModeEnum.DISABLED,
+        enable_wired_table=False,
+        enable_wireless_table=False,
+        enable_chart_recognition=False,
+        enable_formula_recognition=False,
+    ),
+    OCRPresetEnum.DATASHEET: OCRConfig(
+        table_parsing_mode=TableParsingModeEnum.CONSERVATIVE,
+        enable_wired_table=True,
+        enable_wireless_table=False,
+    ),
+    OCRPresetEnum.TABLE_HEAVY: OCRConfig(
+        table_parsing_mode=TableParsingModeEnum.FULL,
+        enable_wired_table=True,
+        enable_wireless_table=True,
+    ),
+    OCRPresetEnum.FORM: OCRConfig(
+        table_parsing_mode=TableParsingModeEnum.CONSERVATIVE,
+        enable_wired_table=True,
+        enable_wireless_table=False,
+    ),
+    OCRPresetEnum.MIXED: OCRConfig(
+        table_parsing_mode=TableParsingModeEnum.CLASSIFICATION_ONLY,
+        enable_wired_table=True,
+        enable_wireless_table=False,
+    ),
+    # CUSTOM uses user-provided config directly
+}
+
+
 class PreprocessingConfig(BaseModel):
     """Preprocessing configuration for layout detection enhancement.
 
@@ -329,6 +462,17 @@ class ProcessingOptions(BaseModel):
         description="Table detection config. If None, all table detection modes are enabled."
     )
 
+    # OCR Processing Preset (OCR track only)
+    # Use presets for optimized configurations or CUSTOM with ocr_config for fine-tuning
+    ocr_preset: Optional[OCRPresetEnum] = Field(
+        default=OCRPresetEnum.DATASHEET,
+        description="OCR processing preset: text_heavy, datasheet, table_heavy, form, mixed, custom"
+    )
+    ocr_config: Optional[OCRConfig] = Field(
+        None,
+        description="Custom OCR config. Used when ocr_preset=custom or to override preset values."
+    )
+
 
 class AnalyzeRequest(BaseModel):
     """Document analysis request"""