synapse-hub 2.2.3 → 2.4.0

package/tools/md_to_xlsx.py

@@ -0,0 +1,307 @@
+#!/usr/bin/env python3
+"""
+Markdown to Excel (.xlsx) Enterprise Converter
+------------------------------------------------
+Parses Markdown Test Case tables and converts them into professional,
+styled Excel workbooks with:
+  - Corporate header styling (Navy Blue, bold, centered)
+  - Color-coded Risk Level (High=Red, Med=Yellow, Low=Green)
+  - Color-coded Priority (Critical/High/Med/Low) and Automatable badges
+  - Frozen top header row (A2 freeze pane)
+  - AutoFilter enabled across all columns
+  - Smart column widths and multi-line text wrapping (replaces <br> with newlines)
+"""
+
+import os
+import sys
+import re
+import argparse
+from typing import List, Dict, Any, Tuple
+
+# UTF-8 terminal encoding
+if hasattr(sys.stdout, 'reconfigure'):
+    try:
+        sys.stdout.reconfigure(encoding='utf-8')
+        sys.stderr.reconfigure(encoding='utf-8')
+    except Exception:
+        pass
+
+try:
+    import openpyxl
+    from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
+    from openpyxl.utils import get_column_letter
+    OPENPYXL_AVAILABLE = True
+except ImportError:
+    OPENPYXL_AVAILABLE = False
+
+
+def clean_cell_content(cell: str) -> str:
+    """Cleans Markdown cell formatting: replaces <br> with newlines, strips backticks."""
+    text = cell.strip()
+    text = re.sub(r'<br\s*/?>', '\n', text, flags=re.IGNORECASE)
+    text = re.sub(r'`([^`]*)`', r'\1', text)
+    # Strip leading/trailing pipes if present in split artifact
+    text = text.strip()
+    return text
+
+
+def parse_markdown_tables(content: str) -> List[Tuple[List[str], List[List[str]]]]:
+    """
+    Parses all Markdown tables in a string.
+    Returns a list of tuples: (headers, rows).
+    """
+    lines = content.splitlines()
+    tables = []
+    
+    current_header = None
+    current_rows = []
+    in_table = False
+    
+    for line in lines:
+        stripped = line.strip()
+        if not stripped.startswith('|') or not stripped.endswith('|'):
+            if in_table and current_header and current_rows:
+                tables.append((current_header, current_rows))
+                current_header = None
+                current_rows = []
+                in_table = False
+            continue
+            
+        # Split cells
+        raw_cells = [c.strip() for c in stripped[1:-1].split('|')]
+        
+        # Check if separator row (|---|---|)
+        if all(re.match(r'^\s*:?-+:?\s*$', c) for c in raw_cells if c):
+            in_table = True
+            continue
+            
+        if not in_table:
+            # First line with pipes is potential header
+            current_header = [clean_cell_content(c) for c in raw_cells]
+        else:
+            # Data row
+            cleaned_row = [clean_cell_content(c) for c in raw_cells]
+            # Ensure row length matches header
+            if current_header:
+                if len(cleaned_row) < len(current_header):
+                    cleaned_row.extend([''] * (len(current_header) - len(cleaned_row)))
+                elif len(cleaned_row) > len(current_header):
+                    cleaned_row = cleaned_row[:len(current_header)]
+            current_rows.append(cleaned_row)
+            
+    if in_table and current_header and current_rows:
+        tables.append((current_header, current_rows))
+        
+    return tables
+
+
+def create_styled_excel(tables: List[Tuple[List[str], List[List[str]]]], output_path: str, sheet_title: str = "Test Cases") -> int:
+    """Builds and styles the Excel workbook using openpyxl."""
+    if not OPENPYXL_AVAILABLE:
+        raise RuntimeError("openpyxl is not installed. Run: pip install openpyxl")
+
+    wb = openpyxl.Workbook()
+    ws = wb.active
+    ws.title = sheet_title[:31]  # Excel limits sheet names to 31 chars
+
+    # Palette
+    NAVY_BLUE = "1F4E78"
+    WHITE = "FFFFFF"
+    BORDER_COLOR = "D9D9D9"
+    
+    # Styles
+    header_fill = PatternFill(start_color=NAVY_BLUE, end_color=NAVY_BLUE, fill_type="solid")
+    header_font = Font(name="Calibri", size=11, bold=True, color=WHITE)
+    header_align = Alignment(horizontal="center", vertical="center", wrap_text=True)
+    
+    cell_border = Border(
+        left=Side(style='thin', color=BORDER_COLOR),
+        right=Side(style='thin', color=BORDER_COLOR),
+        top=Side(style='thin', color=BORDER_COLOR),
+        bottom=Side(style='thin', color=BORDER_COLOR)
+    )
+    
+    # Status badges
+    fill_high = PatternFill(start_color="FCE4D6", fill_type="solid")     # Soft Red
+    font_high = Font(name="Calibri", size=10, bold=True, color="C00000")
+    
+    fill_med = PatternFill(start_color="FFF2CC", fill_type="solid")      # Soft Yellow
+    font_med = Font(name="Calibri", size=10, bold=True, color="B25900")
+    
+    fill_low = PatternFill(start_color="E2EFDA", fill_type="solid")      # Soft Green
+    font_low = Font(name="Calibri", size=10, bold=True, color="375623")
+    
+    fill_yes = PatternFill(start_color="E2EFDA", fill_type="solid")
+    font_yes = Font(name="Calibri", size=10, color="276A3C", bold=True)
+    
+    fill_no = PatternFill(start_color="F2F2F2", fill_type="solid")
+    font_no = Font(name="Calibri", size=10, color="595959")
+
+    # Combine tables if multiple or take the primary table
+    primary_headers = tables[0][0]
+    all_rows = []
+    for h, rows in tables:
+        # If headers match, stack rows; otherwise keep all
+        all_rows.extend(rows)
+
+    # 1. Write Header
+    ws.append(primary_headers)
+    ws.row_dimensions[1].height = 28
+
+    for col_idx in range(1, len(primary_headers) + 1):
+        cell = ws.cell(row=1, column=col_idx)
+        cell.fill = header_fill
+        cell.font = header_font
+        cell.alignment = header_align
+        cell.border = cell_border
+
+    # Standard Column Width Presets
+    width_map = {
+        "tc id": 16,
+        "id": 14,
+        "module": 18,
+        "requirement": 24,
+        "feature": 24,
+        "risk": 12,
+        "risk level": 12,
+        "test title": 36,
+        "title": 36,
+        "scenario": 36,
+        "pre-condition": 28,
+        "test steps": 45,
+        "steps": 45,
+        "expected result": 45,
+        "expected": 45,
+        "priority": 12,
+        "test data": 28,
+        "data": 28,
+        "automatable": 14,
+        "auto type": 12,
+        "tags": 22
+    }
+
+    # Identify column types by header name
+    col_types = {}
+    for idx, header in enumerate(primary_headers, 1):
+        h_lower = header.lower().strip()
+        col_types[idx] = h_lower
+
+    # 2. Write Data Rows
+    current_row_idx = 2
+    for row_data in all_rows:
+        ws.append(row_data)
+        ws.row_dimensions[current_row_idx].height = None  # Auto height for wrapped text
+        
+        for col_idx, val in enumerate(row_data, 1):
+            cell = ws.cell(row=current_row_idx, column=col_idx)
+            cell.border = cell_border
+            cell.font = Font(name="Calibri", size=10)
+            
+            h_name = col_types.get(col_idx, "")
+            val_str = str(val).strip()
+            val_lower = val_str.lower()
+            
+            # Alignments & Styling based on column semantic
+            if any(k in h_name for k in ["steps", "expected", "title", "scenario", "pre-condition"]):
+                cell.alignment = Alignment(horizontal="left", vertical="top", wrap_text=True)
+            elif any(k in h_name for k in ["risk", "priority", "automatable", "auto type", "id"]):
+                cell.alignment = Alignment(horizontal="center", vertical="top")
+            else:
+                cell.alignment = Alignment(horizontal="left", vertical="top")
+
+            # Badges
+            if "risk" in h_name or "priority" in h_name:
+                if "high" in val_lower or "critical" in val_lower:
+                    cell.fill = fill_high
+                    cell.font = font_high
+                elif "med" in val_lower:
+                    cell.fill = fill_med
+                    cell.font = font_med
+                elif "low" in val_lower:
+                    cell.fill = fill_low
+                    cell.font = font_low
+            elif "automatable" in h_name:
+                if val_lower in ["yes", "true"]:
+                    cell.fill = fill_yes
+                    cell.font = font_yes
+                elif val_lower in ["no", "false"]:
+                    cell.fill = fill_no
+                    cell.font = font_no
+                elif "partial" in val_lower:
+                    cell.fill = fill_med
+                    cell.font = font_med
+
+        current_row_idx += 1
+
+    total_rows = len(all_rows)
+
+    # 3. Freeze Header Row
+    ws.freeze_panes = "A2"
+
+    # 4. Enable AutoFilter
+    last_col_letter = get_column_letter(len(primary_headers))
+    ws.auto_filter.ref = f"A1:{last_col_letter}{total_rows + 1}"
+
+    # 5. Set Optimal Column Widths
+    for col_idx, header in enumerate(primary_headers, 1):
+        h_lower = header.lower().strip()
+        col_letter = get_column_letter(col_idx)
+        
+        # Check presets
+        target_width = None
+        for key, width in width_map.items():
+            if key in h_lower:
+                target_width = width
+                break
+                
+        if not target_width:
+            # Dynamic max calculation
+            max_len = len(header)
+            for r in all_rows:
+                if col_idx - 1 < len(r):
+                    lines = str(r[col_idx - 1]).split('\n')
+                    for l in lines:
+                        if len(l) > max_len:
+                            max_len = len(l)
+            target_width = min(max(max_len + 3, 12), 45)
+
+        ws.column_dimensions[col_letter].width = target_width
+
+    # Ensure parent dir exists
+    os.makedirs(os.path.dirname(os.path.abspath(output_path)), exist_ok=True)
+    wb.save(output_path)
+    return total_rows
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Convert Markdown Test Cases into Styled Excel (.xlsx)")
+    parser.add_argument("input", help="Path to input Markdown file (.md)")
+    parser.add_argument("-o", "--output", help="Path to output Excel file (.xlsx). Defaults to same name as input.")
+    parser.add_argument("--sheet-name", default="Test Cases", help="Worksheet title (default: Test Cases)")
+    
+    args = parser.parse_args()
+    
+    if not os.path.exists(args.input):
+        print(f"❌ Error: Input file not found: {args.input}", file=sys.stderr)
+        sys.exit(1)
+        
+    output_path = args.output
+    if not output_path:
+        base, _ = os.path.splitext(args.input)
+        output_path = base + ".xlsx"
+
+    with open(args.input, "r", encoding="utf-8") as f:
+        content = f.read()
+
+    tables = parse_markdown_tables(content)
+    if not tables:
+        print(f"❌ Error: No valid Markdown tables found in {args.input}", file=sys.stderr)
+        sys.exit(1)
+
+    print(f"📖 Found {len(tables)} table(s) in: {args.input}")
+    total = create_styled_excel(tables, output_path, args.sheet_name)
+    print(f"✅ Successfully converted {total} test case(s) to styled Excel: {output_path}")
+
+
+if __name__ == "__main__":
+    main()