thanh-kit 2.5.0

package/templates/skills/document-skills/pdf/scripts/check_bounding_boxes_test.py

@@ -0,0 +1,226 @@
+import unittest
+import json
+import io
+from check_bounding_boxes import get_bounding_box_messages
+
+
+# Currently this is not run automatically in CI; it's just for documentation and manual checking.
+class TestGetBoundingBoxMessages(unittest.TestCase):
+    
+    def create_json_stream(self, data):
+        """Helper to create a JSON stream from data"""
+        return io.StringIO(json.dumps(data))
+    
+    def test_no_intersections(self):
+        """Test case with no bounding box intersections"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30]
+                },
+                {
+                    "description": "Email",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 40, 50, 60],
+                    "entry_bounding_box": [60, 40, 150, 60]
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_label_entry_intersection_same_field(self):
+        """Test intersection between label and entry of the same field"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 60, 30],
+                    "entry_bounding_box": [50, 10, 150, 30]  # Overlaps with label
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_intersection_between_different_fields(self):
+        """Test intersection between bounding boxes of different fields"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30]
+                },
+                {
+                    "description": "Email",
+                    "page_number": 1,
+                    "label_bounding_box": [40, 20, 80, 40],  # Overlaps with Name's boxes
+                    "entry_bounding_box": [160, 10, 250, 30]
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "intersection" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_different_pages_no_intersection(self):
+        """Test that boxes on different pages don't count as intersecting"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30]
+                },
+                {
+                    "description": "Email",
+                    "page_number": 2,
+                    "label_bounding_box": [10, 10, 50, 30],  # Same coordinates but different page
+                    "entry_bounding_box": [60, 10, 150, 30]
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_entry_height_too_small(self):
+        """Test that entry box height is checked against font size"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 20],  # Height is 10
+                    "entry_text": {
+                        "font_size": 14  # Font size larger than height
+                    }
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_entry_height_adequate(self):
+        """Test that adequate entry box height passes"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 30],  # Height is 20
+                    "entry_text": {
+                        "font_size": 14  # Font size smaller than height
+                    }
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_default_font_size(self):
+        """Test that default font size is used when not specified"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 20],  # Height is 10
+                    "entry_text": {}  # No font_size specified, should use default 14
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("FAILURE" in msg and "height" in msg for msg in messages))
+        self.assertFalse(any("SUCCESS" in msg for msg in messages))
+    
+    def test_no_entry_text(self):
+        """Test that missing entry_text doesn't cause height check"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [60, 10, 150, 20]  # Small height but no entry_text
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+    def test_multiple_errors_limit(self):
+        """Test that error messages are limited to prevent excessive output"""
+        fields = []
+        # Create many overlapping fields
+        for i in range(25):
+            fields.append({
+                "description": f"Field{i}",
+                "page_number": 1,
+                "label_bounding_box": [10, 10, 50, 30],  # All overlap
+                "entry_bounding_box": [20, 15, 60, 35]   # All overlap
+            })
+        
+        data = {"form_fields": fields}
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        # Should abort after ~20 messages
+        self.assertTrue(any("Aborting" in msg for msg in messages))
+        # Should have some FAILURE messages but not hundreds
+        failure_count = sum(1 for msg in messages if "FAILURE" in msg)
+        self.assertGreater(failure_count, 0)
+        self.assertLess(len(messages), 30)  # Should be limited
+    
+    def test_edge_touching_boxes(self):
+        """Test that boxes touching at edges don't count as intersecting"""
+        data = {
+            "form_fields": [
+                {
+                    "description": "Name",
+                    "page_number": 1,
+                    "label_bounding_box": [10, 10, 50, 30],
+                    "entry_bounding_box": [50, 10, 150, 30]  # Touches at x=50
+                }
+            ]
+        }
+        
+        stream = self.create_json_stream(data)
+        messages = get_bounding_box_messages(stream)
+        self.assertTrue(any("SUCCESS" in msg for msg in messages))
+        self.assertFalse(any("FAILURE" in msg for msg in messages))
+    
+
+if __name__ == '__main__':
+    unittest.main()

package/templates/skills/document-skills/pdf/scripts/check_fillable_fields.py

@@ -0,0 +1,12 @@
+import sys
+from pypdf import PdfReader
+
+
+# Script for Claude to run to determine whether a PDF has fillable form fields. See forms.md.
+
+
+reader = PdfReader(sys.argv[1])
+if (reader.get_fields()):
+    print("This PDF has fillable form fields")
+else:
+    print("This PDF does not have fillable form fields; you will need to visually determine where to enter data")

package/templates/skills/document-skills/pdf/scripts/convert_pdf_to_images.py

@@ -0,0 +1,35 @@
+import os
+import sys
+
+from pdf2image import convert_from_path
+
+
+# Converts each page of a PDF to a PNG image.
+
+
+def convert(pdf_path, output_dir, max_dim=1000):
+    images = convert_from_path(pdf_path, dpi=200)
+
+    for i, image in enumerate(images):
+        # Scale image if needed to keep width/height under `max_dim`
+        width, height = image.size
+        if width > max_dim or height > max_dim:
+            scale_factor = min(max_dim / width, max_dim / height)
+            new_width = int(width * scale_factor)
+            new_height = int(height * scale_factor)
+            image = image.resize((new_width, new_height))
+        
+        image_path = os.path.join(output_dir, f"page_{i+1}.png")
+        image.save(image_path)
+        print(f"Saved page {i+1} as {image_path} (size: {image.size})")
+
+    print(f"Converted {len(images)} pages to PNG images")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print("Usage: convert_pdf_to_images.py [input pdf] [output directory]")
+        sys.exit(1)
+    pdf_path = sys.argv[1]
+    output_directory = sys.argv[2]
+    convert(pdf_path, output_directory)

package/templates/skills/document-skills/pdf/scripts/create_validation_image.py

@@ -0,0 +1,41 @@
+import json
+import sys
+
+from PIL import Image, ImageDraw
+
+
+# Creates "validation" images with rectangles for the bounding box information that
+# Claude creates when determining where to add text annotations in PDFs. See forms.md.
+
+
+def create_validation_image(page_number, fields_json_path, input_path, output_path):
+    # Input file should be in the `fields.json` format described in forms.md.
+    with open(fields_json_path, 'r') as f:
+        data = json.load(f)
+
+        img = Image.open(input_path)
+        draw = ImageDraw.Draw(img)
+        num_boxes = 0
+        
+        for field in data["form_fields"]:
+            if field["page_number"] == page_number:
+                entry_box = field['entry_bounding_box']
+                label_box = field['label_bounding_box']
+                # Draw red rectangle over entry bounding box and blue rectangle over the label.
+                draw.rectangle(entry_box, outline='red', width=2)
+                draw.rectangle(label_box, outline='blue', width=2)
+                num_boxes += 2
+        
+        img.save(output_path)
+        print(f"Created validation image at {output_path} with {num_boxes} bounding boxes")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 5:
+        print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]")
+        sys.exit(1)
+    page_number = int(sys.argv[1])
+    fields_json_path = sys.argv[2]
+    input_image_path = sys.argv[3]
+    output_image_path = sys.argv[4]
+    create_validation_image(page_number, fields_json_path, input_image_path, output_image_path)

package/templates/skills/document-skills/pdf/scripts/extract_form_field_info.py

@@ -0,0 +1,152 @@
+import json
+import sys
+
+from pypdf import PdfReader
+
+
+# Extracts data for the fillable form fields in a PDF and outputs JSON that
+# Claude uses to fill the fields. See forms.md.
+
+
+# This matches the format used by PdfReader `get_fields` and `update_page_form_field_values` methods.
+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"  # radio groups handled separately
+        states = field.get("/_States_", [])
+        if len(states) == 2:
+            # "/Off" seems to always be the unchecked value, as suggested by
+            # https://opensource.adobe.com/dc-acrobat-sdk-docs/standards/pdfstandards/pdf/PDF32000_2008.pdf#page=448
+            # It can be either first or second in the "/_States_" list.
+            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
+
+
+# Returns a list of fillable PDF fields:
+# [
+#   {
+#     "field_id": "name",
+#     "page": 1,
+#     "type": ("text", "checkbox", "radio_group", or "choice")
+#     // Per-type additional fields described in forms.md
+#   },
+# ]
+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():
+        # Skip if this is a container field with children, except that it might be
+        # a parent group for radio button options.
+        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)
+
+    # Bounding rects are stored in annotations in page objects.
+
+    # Radio button options have a separate annotation for each choice;
+    # all choices have the same field name.
+    # See https://westhealth.github.io/exploring-fillable-forms-with-pdfrw.html
+    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:
+                    # ann['/AP']['/N'] should have two items. One of them is '/Off',
+                    # the other is the active value.
+                    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": [],
+                        }
+                    # Note: at least on macOS 15.7, Preview.app doesn't show selected
+                    # radio buttons correctly. (It does if you remove the leading slash
+                    # from the value, but that causes them not to appear correctly in
+                    # Chrome/Firefox/Acrobat/etc).
+                    radio_fields_by_id[field_id]["radio_options"].append({
+                        "value": on_values[0],
+                        "rect": rect,
+                    })
+
+    # Some PDFs have form field definitions without corresponding annotations,
+    # so we can't tell where they are. Ignore these fields for now.
+    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")
+
+    # Sort by page number, then Y position (flipped in PDF coordinate system), then X.
+    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/templates/skills/document-skills/pdf/scripts/fill_fillable_fields.py

@@ -0,0 +1,114 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+
+from extract_form_field_info import get_field_info
+
+
+# Fills fillable form fields in a PDF. See forms.md.
+
+
+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)
+    # Group by page number.
+    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)
+
+    # This seems to be necessary for many PDF viewers to format the form values correctly.
+    # It may cause the viewer to show a "save changes" dialog even if the user doesn't make any changes.
+    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
+
+
+# pypdf (at least version 5.7.0) has a bug when setting the value for a selection list field.
+# In _writer.py around line 966:
+#
+# if field.get(FA.FT, "/Tx") == "/Ch" and field_flags & FA.FfBits.Combo == 0:
+#     txt = "\n".join(annotation.get_inherited(FA.Opt, []))
+#
+# The problem is that for selection lists, `get_inherited` returns a list of two-element lists like
+# [["value1", "Text 1"], ["value2", "Text 2"], ...]
+# This causes `join` to throw a TypeError because it expects an iterable of strings.
+# The horrible workaround is to patch `get_inherited` to return a list of the value strings.
+# We call the original method and adjust the return value only if the argument to `get_inherited`
+# is `FA.Opt` and if the return value is a list of two-element lists.
+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)