sophhub 0.2.0 → 0.2.2

package/skills/sophnet-pdf/src/scripts/extract_form_field_info.py

@@ -0,0 +1,122 @@
+import json
+import sys
+
+from pypdf import PdfReader
+
+
+
+
+def get_full_annotation_field_id(annotation):
+    components = []
+    while annotation:
+        field_name = annotation.get('/T')
+        if field_name:
+            components.append(field_name)
+        annotation = annotation.get('/Parent')
+    return ".".join(reversed(components)) if components else None
+
+
+def make_field_dict(field, field_id):
+    field_dict = {"field_id": field_id}
+    ft = field.get('/FT')
+    if ft == "/Tx":
+        field_dict["type"] = "text"
+    elif ft == "/Btn":
+        field_dict["type"] = "checkbox"  
+        states = field.get("/_States_", [])
+        if len(states) == 2:
+            if "/Off" in states:
+                field_dict["checked_value"] = states[0] if states[0] != "/Off" else states[1]
+                field_dict["unchecked_value"] = "/Off"
+            else:
+                print(f"Unexpected state values for checkbox `${field_id}`. Its checked and unchecked values may not be correct; if you're trying to check it, visually verify the results.")
+                field_dict["checked_value"] = states[0]
+                field_dict["unchecked_value"] = states[1]
+    elif ft == "/Ch":
+        field_dict["type"] = "choice"
+        states = field.get("/_States_", [])
+        field_dict["choice_options"] = [{
+            "value": state[0],
+            "text": state[1],
+        } for state in states]
+    else:
+        field_dict["type"] = f"unknown ({ft})"
+    return field_dict
+
+
+def get_field_info(reader: PdfReader):
+    fields = reader.get_fields()
+
+    field_info_by_id = {}
+    possible_radio_names = set()
+
+    for field_id, field in fields.items():
+        if field.get("/Kids"):
+            if field.get("/FT") == "/Btn":
+                possible_radio_names.add(field_id)
+            continue
+        field_info_by_id[field_id] = make_field_dict(field, field_id)
+
+
+    radio_fields_by_id = {}
+
+    for page_index, page in enumerate(reader.pages):
+        annotations = page.get('/Annots', [])
+        for ann in annotations:
+            field_id = get_full_annotation_field_id(ann)
+            if field_id in field_info_by_id:
+                field_info_by_id[field_id]["page"] = page_index + 1
+                field_info_by_id[field_id]["rect"] = ann.get('/Rect')
+            elif field_id in possible_radio_names:
+                try:
+                    on_values = [v for v in ann["/AP"]["/N"] if v != "/Off"]
+                except KeyError:
+                    continue
+                if len(on_values) == 1:
+                    rect = ann.get("/Rect")
+                    if field_id not in radio_fields_by_id:
+                        radio_fields_by_id[field_id] = {
+                            "field_id": field_id,
+                            "type": "radio_group",
+                            "page": page_index + 1,
+                            "radio_options": [],
+                        }
+                    radio_fields_by_id[field_id]["radio_options"].append({
+                        "value": on_values[0],
+                        "rect": rect,
+                    })
+
+    fields_with_location = []
+    for field_info in field_info_by_id.values():
+        if "page" in field_info:
+            fields_with_location.append(field_info)
+        else:
+            print(f"Unable to determine location for field id: {field_info.get('field_id')}, ignoring")
+
+    def sort_key(f):
+        if "radio_options" in f:
+            rect = f["radio_options"][0]["rect"] or [0, 0, 0, 0]
+        else:
+            rect = f.get("rect") or [0, 0, 0, 0]
+        adjusted_position = [-rect[1], rect[0]]
+        return [f.get("page"), adjusted_position]
+    
+    sorted_fields = fields_with_location + list(radio_fields_by_id.values())
+    sorted_fields.sort(key=sort_key)
+
+    return sorted_fields
+
+
+def write_field_info(pdf_path: str, json_output_path: str):
+    reader = PdfReader(pdf_path)
+    field_info = get_field_info(reader)
+    with open(json_output_path, "w") as f:
+        json.dump(field_info, f, indent=2)
+    print(f"Wrote {len(field_info)} fields to {json_output_path}")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: extract_form_field_info.py [input pdf] [output json]")
+        sys.exit(1)
+    write_field_info(sys.argv[1], sys.argv[2])

package/skills/sophnet-pdf/src/scripts/extract_form_structure.py

@@ -0,0 +1,115 @@
+"""
+Extract form structure from a non-fillable PDF.
+
+This script analyzes the PDF to find:
+- Text labels with their exact coordinates
+- Horizontal lines (row boundaries)
+- Checkboxes (small rectangles)
+
+Output: A JSON file with the form structure that can be used to generate
+accurate field coordinates for filling.
+
+Usage: python extract_form_structure.py <input.pdf> <output.json>
+"""
+
+import json
+import sys
+import pdfplumber
+
+
+def extract_form_structure(pdf_path):
+    structure = {
+        "pages": [],
+        "labels": [],
+        "lines": [],
+        "checkboxes": [],
+        "row_boundaries": []
+    }
+
+    with pdfplumber.open(pdf_path) as pdf:
+        for page_num, page in enumerate(pdf.pages, 1):
+            structure["pages"].append({
+                "page_number": page_num,
+                "width": float(page.width),
+                "height": float(page.height)
+            })
+
+            words = page.extract_words()
+            for word in words:
+                structure["labels"].append({
+                    "page": page_num,
+                    "text": word["text"],
+                    "x0": round(float(word["x0"]), 1),
+                    "top": round(float(word["top"]), 1),
+                    "x1": round(float(word["x1"]), 1),
+                    "bottom": round(float(word["bottom"]), 1)
+                })
+
+            for line in page.lines:
+                if abs(float(line["x1"]) - float(line["x0"])) > page.width * 0.5:
+                    structure["lines"].append({
+                        "page": page_num,
+                        "y": round(float(line["top"]), 1),
+                        "x0": round(float(line["x0"]), 1),
+                        "x1": round(float(line["x1"]), 1)
+                    })
+
+            for rect in page.rects:
+                width = float(rect["x1"]) - float(rect["x0"])
+                height = float(rect["bottom"]) - float(rect["top"])
+                if 5 <= width <= 15 and 5 <= height <= 15 and abs(width - height) < 2:
+                    structure["checkboxes"].append({
+                        "page": page_num,
+                        "x0": round(float(rect["x0"]), 1),
+                        "top": round(float(rect["top"]), 1),
+                        "x1": round(float(rect["x1"]), 1),
+                        "bottom": round(float(rect["bottom"]), 1),
+                        "center_x": round((float(rect["x0"]) + float(rect["x1"])) / 2, 1),
+                        "center_y": round((float(rect["top"]) + float(rect["bottom"])) / 2, 1)
+                    })
+
+    lines_by_page = {}
+    for line in structure["lines"]:
+        page = line["page"]
+        if page not in lines_by_page:
+            lines_by_page[page] = []
+        lines_by_page[page].append(line["y"])
+
+    for page, y_coords in lines_by_page.items():
+        y_coords = sorted(set(y_coords))
+        for i in range(len(y_coords) - 1):
+            structure["row_boundaries"].append({
+                "page": page,
+                "row_top": y_coords[i],
+                "row_bottom": y_coords[i + 1],
+                "row_height": round(y_coords[i + 1] - y_coords[i], 1)
+            })
+
+    return structure
+
+
+def main():
+    if len(sys.argv) != 3:
+        print("Usage: extract_form_structure.py <input.pdf> <output.json>")
+        sys.exit(1)
+
+    pdf_path = sys.argv[1]
+    output_path = sys.argv[2]
+
+    print(f"Extracting structure from {pdf_path}...")
+    structure = extract_form_structure(pdf_path)
+
+    with open(output_path, "w") as f:
+        json.dump(structure, f, indent=2)
+
+    print(f"Found:")
+    print(f"  - {len(structure['pages'])} pages")
+    print(f"  - {len(structure['labels'])} text labels")
+    print(f"  - {len(structure['lines'])} horizontal lines")
+    print(f"  - {len(structure['checkboxes'])} checkboxes")
+    print(f"  - {len(structure['row_boundaries'])} row boundaries")
+    print(f"Saved to {output_path}")
+
+
+if __name__ == "__main__":
+    main()

package/skills/sophnet-pdf/src/scripts/extract_pdf_content.py

@@ -0,0 +1,35 @@
+#!/usr/bin/env python3
+"""Extract text from PDF to understand its content."""
+
+import pdfplumber
+import sys
+
+pdf_path = "/Data/shutong.shan/clawd/media/inbound/documents/Image-Edit_教程.pdf"
+
+try:
+    with pdfplumber.open(pdf_path) as pdf:
+        print(f"Total pages: {len(pdf.pages)}\n")
+        print("=" * 80)
+        print("PDF Content:")
+        print("=" * 80 + "\n")
+
+        for i, page in enumerate(pdf.pages, 1):
+            print(f"\n--- Page {i} ---\n")
+            text = page.extract_text()
+            if text:
+                print(text)
+            else:
+                print("[No text found on this page]")
+
+            # Check for tables
+            tables = page.extract_tables()
+            if tables:
+                print(f"\n[Found {len(tables)} table(s) on this page]")
+                for j, table in enumerate(tables, 1):
+                    print(f"\nTable {j}:")
+                    for row in table:
+                        print(row)
+
+except Exception as e:
+    print(f"Error: {e}", file=sys.stderr)
+    sys.exit(1)

package/skills/sophnet-pdf/src/scripts/fill_fillable_fields.py

@@ -0,0 +1,98 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+
+from extract_form_field_info import get_field_info
+
+
+
+
+def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str):
+    with open(fields_json_path) as f:
+        fields = json.load(f)
+    fields_by_page = {}
+    for field in fields:
+        if "value" in field:
+            field_id = field["field_id"]
+            page = field["page"]
+            if page not in fields_by_page:
+                fields_by_page[page] = {}
+            fields_by_page[page][field_id] = field["value"]
+    
+    reader = PdfReader(input_pdf_path)
+
+    has_error = False
+    field_info = get_field_info(reader)
+    fields_by_ids = {f["field_id"]: f for f in field_info}
+    for field in fields:
+        existing_field = fields_by_ids.get(field["field_id"])
+        if not existing_field:
+            has_error = True
+            print(f"ERROR: `{field['field_id']}` is not a valid field ID")
+        elif field["page"] != existing_field["page"]:
+            has_error = True
+            print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})")
+        else:
+            if "value" in field:
+                err = validation_error_for_field_value(existing_field, field["value"])
+                if err:
+                    print(err)
+                    has_error = True
+    if has_error:
+        sys.exit(1)
+
+    writer = PdfWriter(clone_from=reader)
+    for page, field_values in fields_by_page.items():
+        writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False)
+
+    writer.set_need_appearances_writer(True)
+    
+    with open(output_pdf_path, "wb") as f:
+        writer.write(f)
+
+
+def validation_error_for_field_value(field_info, field_value):
+    field_type = field_info["type"]
+    field_id = field_info["field_id"]
+    if field_type == "checkbox":
+        checked_val = field_info["checked_value"]
+        unchecked_val = field_info["unchecked_value"]
+        if field_value != checked_val and field_value != unchecked_val:
+            return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"'
+    elif field_type == "radio_group":
+        option_values = [opt["value"] for opt in field_info["radio_options"]]
+        if field_value not in option_values:
+            return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}' 
+    elif field_type == "choice":
+        choice_values = [opt["value"] for opt in field_info["choice_options"]]
+        if field_value not in choice_values:
+            return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}'
+    return None
+
+
+def monkeypatch_pydpf_method():
+    from pypdf.generic import DictionaryObject
+    from pypdf.constants import FieldDictionaryAttributes
+
+    original_get_inherited = DictionaryObject.get_inherited
+
+    def patched_get_inherited(self, key: str, default = None):
+        result = original_get_inherited(self, key, default)
+        if key == FieldDictionaryAttributes.Opt:
+            if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result):
+                result = [r[0] for r in result]
+        return result
+
+    DictionaryObject.get_inherited = patched_get_inherited
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]")
+        sys.exit(1)
+    monkeypatch_pydpf_method()
+    input_pdf = sys.argv[1]
+    fields_json = sys.argv[2]
+    output_pdf = sys.argv[3]
+    fill_pdf_fields(input_pdf, fields_json, output_pdf)

package/skills/sophnet-pdf/src/scripts/fill_pdf_form_with_annotations.py

@@ -0,0 +1,107 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+from pypdf.annotations import FreeText
+
+
+
+
+def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height):
+    x_scale = pdf_width / image_width
+    y_scale = pdf_height / image_height
+
+    left = bbox[0] * x_scale
+    right = bbox[2] * x_scale
+
+    top = pdf_height - (bbox[1] * y_scale)
+    bottom = pdf_height - (bbox[3] * y_scale)
+
+    return left, bottom, right, top
+
+
+def transform_from_pdf_coords(bbox, pdf_height):
+    left = bbox[0]
+    right = bbox[2]
+
+    pypdf_top = pdf_height - bbox[1]      
+    pypdf_bottom = pdf_height - bbox[3]   
+
+    return left, pypdf_bottom, right, pypdf_top
+
+
+def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
+    
+    with open(fields_json_path, "r") as f:
+        fields_data = json.load(f)
+    
+    reader = PdfReader(input_pdf_path)
+    writer = PdfWriter()
+    
+    writer.append(reader)
+    
+    pdf_dimensions = {}
+    for i, page in enumerate(reader.pages):
+        mediabox = page.mediabox
+        pdf_dimensions[i + 1] = [mediabox.width, mediabox.height]
+    
+    annotations = []
+    for field in fields_data["form_fields"]:
+        page_num = field["page_number"]
+
+        page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num)
+        pdf_width, pdf_height = pdf_dimensions[page_num]
+
+        if "pdf_width" in page_info:
+            transformed_entry_box = transform_from_pdf_coords(
+                field["entry_bounding_box"],
+                float(pdf_height)
+            )
+        else:
+            image_width = page_info["image_width"]
+            image_height = page_info["image_height"]
+            transformed_entry_box = transform_from_image_coords(
+                field["entry_bounding_box"],
+                image_width, image_height,
+                float(pdf_width), float(pdf_height)
+            )
+        
+        if "entry_text" not in field or "text" not in field["entry_text"]:
+            continue
+        entry_text = field["entry_text"]
+        text = entry_text["text"]
+        if not text:
+            continue
+        
+        font_name = entry_text.get("font", "Arial")
+        font_size = str(entry_text.get("font_size", 14)) + "pt"
+        font_color = entry_text.get("font_color", "000000")
+
+        annotation = FreeText(
+            text=text,
+            rect=transformed_entry_box,
+            font=font_name,
+            font_size=font_size,
+            font_color=font_color,
+            border_color=None,
+            background_color=None,
+        )
+        annotations.append(annotation)
+        writer.add_annotation(page_number=page_num - 1, annotation=annotation)
+        
+    with open(output_pdf_path, "wb") as output:
+        writer.write(output)
+    
+    print(f"Successfully filled PDF form and saved to {output_pdf_path}")
+    print(f"Added {len(annotations)} text annotations")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]")
+        sys.exit(1)
+    input_pdf = sys.argv[1]
+    fields_json = sys.argv[2]
+    output_pdf = sys.argv[3]
+    
+    fill_pdf_form(input_pdf, fields_json, output_pdf)

package/skills/sophnet-pdf/src/scripts/upload_file.sh

@@ -0,0 +1,88 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+usage() {
+  cat <<'USAGE'
+Usage:
+  bash upload_file.sh --file "/path/to/file.pdf" [options]
+
+Options:
+  --file "/path/to/file.pdf"   Required. Local file path to upload.
+  --timeout 60                 Optional. Upload timeout in seconds. Default: 60.
+USAGE
+}
+
+FILE_PATH=""
+TIMEOUT="60"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SKILL_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --file)
+      FILE_PATH="$2"
+      shift 2
+      ;;
+    --timeout)
+      TIMEOUT="$2"
+      shift 2
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      # Handle unquoted file paths split by shell (e.g. spaces in Chinese filenames)
+      if [[ -n "$FILE_PATH" && "$1" != -* ]]; then
+        FILE_PATH="$FILE_PATH $1"
+      else
+        echo "Unknown argument: $1" >&2
+        usage
+        exit 1
+      fi
+      shift
+      ;;
+  esac
+done
+
+if [[ -z "$FILE_PATH" ]]; then
+  echo "Error: --file is required." >&2
+  exit 1
+fi
+
+bash "$SCRIPT_DIR/ensure_uv_env.sh" --quiet
+
+if command -v realpath >/dev/null 2>&1; then
+  ABS_FILE_PATH="$(realpath "$FILE_PATH")"
+elif command -v readlink >/dev/null 2>&1; then
+  ABS_FILE_PATH="$(readlink -f "$FILE_PATH")"
+else
+  ABS_FILE_PATH="$(uv run --project "$SKILL_DIR" python -c 'from pathlib import Path; import sys; print(Path(sys.argv[1]).expanduser().resolve())' "$FILE_PATH")"
+fi
+
+if [[ ! -f "$ABS_FILE_PATH" ]]; then
+  echo "Error: file not found: $ABS_FILE_PATH" >&2
+  exit 1
+fi
+
+if [[ "$ABS_FILE_PATH" != *.pdf ]]; then
+  echo "Error: expected a .pdf file: $ABS_FILE_PATH" >&2
+  exit 1
+fi
+
+signed_url="$(uv run --project "$SKILL_DIR" python -c "
+import sophnet_tools, sys
+u = sophnet_tools.upload_oss(sys.argv[1], timeout=int(sys.argv[2]))
+print(u if u else '')
+" "$ABS_FILE_PATH" "$TIMEOUT" 2>/dev/null || true)"
+
+if [[ -z "$signed_url" ]]; then
+  echo "FILE_PATH=$ABS_FILE_PATH"
+  echo "UPLOAD_STATUS=skipped"
+  echo "ERROR=upload_failed"
+  exit 0
+fi
+
+echo "FILE_PATH=$ABS_FILE_PATH"
+echo "UPLOAD_STATUS=uploaded"
+echo "DOWNLOAD_URL=$signed_url"