mercury-agent 0.5.0 → 0.5.2

package/examples/extensions/pdf/skill/scripts/extract_form_structure.py

@@ -1,115 +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()
+"""
+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/examples/extensions/pdf/skill/scripts/fill_fillable_fields.py

@@ -1,98 +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)
+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/examples/extensions/pdf/skill/scripts/fill_pdf_form_with_annotations.py

@@ -1,107 +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)
+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)