This tool extracts scale information from Bluebeam-calibrated PDF files. It identifies scale ruler values, drawing scale annotations, and slope annotations embedded in the PDF metadata.

extract_pdf_scales.py

#!/usr/bin/env python3
"""

extract_pdf_scales.py
This tool extracts scale information from Bluebeam-calibrated PDF files. It identifies scale ruler values, drawing scale annotations, and slope annotations embedded in the PDF metadata.
qpdf: https://github.com/qpdf/qpdf

Usage:
    python extract_pdf_scales.py file.json
    
Author: Madhukar Moogala

## Prerequisites
- Python 3.x installed
- qpdf command-line tool installed
- Bluebeam-calibrated PDF file

## Usage Instructions

### Step 1: Convert PDF to JSON
Generate JSON data from your PDF using qpdf:
```bash
qpdf --json --json-stream-data=inline your_file.pdf > file.json
```

### Step 2: Run the Python Script
Extract scale information:
```bash
python extract_pdf_scales.py file.json
```

## Output
The script will display:
1. **Scale Ruler Values** - All measurement scales available in Bluebeam (e.g., 1/4" = 1', 1:48 ratio)
2. **Drawing Scale Annotations** - Actual scales used on specific drawings
3. **Slope Annotations** - Roof slopes and construction details (e.g., SLOPE 4:12)
4. **Summary** - Total counts and PDF information

## Example Output
```
============================================================
PDF SCALE EXTRACTION RESULTS
============================================================
Total Pages: 15

1. SCALE RULER VALUES (15 found):
----------------------------------------
 1. 0.03125" = 1' (1:384 ) - obj:2863 0 R
 2. 0.0625" = 1' (1:192 ) - obj:2865 0 R
 3. 0.25" = 1'   (1:48  ) - obj:2861 0 R
 ...

2. DRAWING SCALE ANNOTATIONS (9 found):
----------------------------------------
    SCALE: 1/2"=1'-0"
    (Found in 9 locations)

3. SLOPE ANNOTATIONS (4 found):
----------------------------------------
    SLOPE 4:12
    (Found in 4 locations)
```
"""

import json
import sys
import re
from collections import defaultdict

if len(sys.argv) < 2:
    print("Usage: python extract_pdf_scales.py file.json")
    sys.exit(1)


def main():
    json_file = sys.argv[1]

    with open(json_file, "r", encoding="utf-8") as fh:
        data = json.load(fh)

    print("=" * 60)
    print("PDF SCALE EXTRACTION RESULTS")
    print("=" * 60)

    # Get page information
    pages = data.get("pages", [])
    print(f"Total Pages: {len(pages)}")

    # Extract scale information
    qpdf_list = data.get("qpdf", [])
    if len(qpdf_list) < 2:
        print("No object data found")
        return

    objects_dict = qpdf_list[1]

    # Find scale ruler values (/R fields)
    scale_rulers = []
    scale_annotations = []
    slope_annotations = []

    for key, obj in objects_dict.items():
        if key.startswith("obj:") and isinstance(obj, dict):
            value = obj.get("value")
            if isinstance(value, dict):
                # Scale ruler values
                r_field = value.get("/R")
                if isinstance(r_field, str) and "in = 1 ft" in r_field:
                    match = re.search(r"(\d*\.?\d+)\s*in\s*=\s*1\s*ft", r_field)
                    if match:
                        inches = float(match.group(1))
                        ratio = int(12 / inches)
                        scale_rulers.append(
                            {
                                "inches": inches,
                                "scale": f"{inches}\" = 1'",
                                "ratio": f"1:{ratio}",
                                "object": key,
                            }
                        )

                # Scale annotations
                contents = value.get("/Contents")
                if isinstance(contents, str):
                    if "SCALE:" in contents and "=" in contents:
                        scale_annotations.append(
                            {"content": contents.replace("u:", ""), "object": key}
                        )
                    elif "SLOPE" in contents and ":" in contents:
                        slope_annotations.append(
                            {"content": contents.replace("u:", ""), "object": key}
                        )

    # Sort scale rulers by size
    scale_rulers.sort(key=lambda x: x["inches"])

    # Display results
    print(f"\n1. SCALE RULER VALUES ({len(scale_rulers)} found):")
    print("-" * 40)
    for i, scale in enumerate(scale_rulers, 1):
        print(f"{i:2d}. {scale['scale']:12} ({scale['ratio']:6}) - {scale['object']}")

    if scale_annotations:
        print(f"\n2. DRAWING SCALE ANNOTATIONS ({len(scale_annotations)} found):")
        print("-" * 40)
        unique_scales = set()
        for annotation in scale_annotations:
            if annotation["content"] not in unique_scales:
                unique_scales.add(annotation["content"])
                print(f"    {annotation['content']}")
        print(f"    (Found in {len(scale_annotations)} locations)")

    if slope_annotations:
        print(f"\n3. SLOPE ANNOTATIONS ({len(slope_annotations)} found):")
        print("-" * 40)
        unique_slopes = set()
        for annotation in slope_annotations:
            if annotation["content"] not in unique_slopes:
                unique_slopes.add(annotation["content"])
                print(f"    {annotation['content']}")
        print(f"    (Found in {len(slope_annotations)} locations)")

    # Summary
    print(f"\n" + "=" * 60)
    print("SUMMARY:")
    print(f"• {len(scale_rulers)} scale ruler increments (for measurements)")
    print(
        f"• {len(set(s['content'] for s in scale_annotations))} unique drawing scales"
    )
    print(
        f"• {len(set(s['content'] for s in slope_annotations))} unique slope annotations"
    )
    print(f"• {len(pages)} total pages in PDF")
    print("=" * 60)


if __name__ == "__main__":
    main()