mercury-agent 0.5.0 → 0.5.2

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

@@ -1,65 +1,65 @@
-from dataclasses import dataclass
-import json
-import sys
-
-
-
-
-@dataclass
-class RectAndField:
-    rect: list[float]
-    rect_type: str
-    field: dict
-
-
-def get_bounding_box_messages(fields_json_stream) -> list[str]:
-    messages = []
-    fields = json.load(fields_json_stream)
-    messages.append(f"Read {len(fields['form_fields'])} fields")
-
-    def rects_intersect(r1, r2):
-        disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0]
-        disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1]
-        return not (disjoint_horizontal or disjoint_vertical)
-
-    rects_and_fields = []
-    for f in fields["form_fields"]:
-        rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f))
-        rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f))
-
-    has_error = False
-    for i, ri in enumerate(rects_and_fields):
-        for j in range(i + 1, len(rects_and_fields)):
-            rj = rects_and_fields[j]
-            if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect):
-                has_error = True
-                if ri.field is rj.field:
-                    messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})")
-                else:
-                    messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})")
-                if len(messages) >= 20:
-                    messages.append("Aborting further checks; fix bounding boxes and try again")
-                    return messages
-        if ri.rect_type == "entry":
-            if "entry_text" in ri.field:
-                font_size = ri.field["entry_text"].get("font_size", 14)
-                entry_height = ri.rect[3] - ri.rect[1]
-                if entry_height < font_size:
-                    has_error = True
-                    messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.")
-                    if len(messages) >= 20:
-                        messages.append("Aborting further checks; fix bounding boxes and try again")
-                        return messages
-
-    if not has_error:
-        messages.append("SUCCESS: All bounding boxes are valid")
-    return messages
-
-if __name__ == "__main__":
-    if len(sys.argv) != 2:
-        print("Usage: check_bounding_boxes.py [fields.json]")
-        sys.exit(1)
-    with open(sys.argv[1]) as f:
-        messages = get_bounding_box_messages(f)
-    for msg in messages:
-        print(msg)
+from dataclasses import dataclass
+import json
+import sys
+
+
+
+
+@dataclass
+class RectAndField:
+    rect: list[float]
+    rect_type: str
+    field: dict
+
+
+def get_bounding_box_messages(fields_json_stream) -> list[str]:
+    messages = []
+    fields = json.load(fields_json_stream)
+    messages.append(f"Read {len(fields['form_fields'])} fields")
+
+    def rects_intersect(r1, r2):
+        disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0]
+        disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1]
+        return not (disjoint_horizontal or disjoint_vertical)
+
+    rects_and_fields = []
+    for f in fields["form_fields"]:
+        rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f))
+        rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f))
+
+    has_error = False
+    for i, ri in enumerate(rects_and_fields):
+        for j in range(i + 1, len(rects_and_fields)):
+            rj = rects_and_fields[j]
+            if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect):
+                has_error = True
+                if ri.field is rj.field:
+                    messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})")
+                else:
+                    messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})")
+                if len(messages) >= 20:
+                    messages.append("Aborting further checks; fix bounding boxes and try again")
+                    return messages
+        if ri.rect_type == "entry":
+            if "entry_text" in ri.field:
+                font_size = ri.field["entry_text"].get("font_size", 14)
+                entry_height = ri.rect[3] - ri.rect[1]
+                if entry_height < font_size:
+                    has_error = True
+                    messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.")
+                    if len(messages) >= 20:
+                        messages.append("Aborting further checks; fix bounding boxes and try again")
+                        return messages
+
+    if not has_error:
+        messages.append("SUCCESS: All bounding boxes are valid")
+    return messages
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: check_bounding_boxes.py [fields.json]")
+        sys.exit(1)
+    with open(sys.argv[1]) as f:
+        messages = get_bounding_box_messages(f)
+    for msg in messages:
+        print(msg)

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

@@ -1,11 +1,11 @@
-import sys
-from pypdf import PdfReader
-
-
-
-
-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")
+import sys
+from pypdf import PdfReader
+
+
+
+
+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/examples/extensions/pdf/skill/scripts/convert_pdf_to_images.py

@@ -1,33 +1,33 @@
-import os
-import sys
-
-from pdf2image import convert_from_path
-
-
-
-
-def convert(pdf_path, output_dir, max_dim=1000):
-    images = convert_from_path(pdf_path, dpi=200)
-
-    for i, image in enumerate(images):
-        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)
+import os
+import sys
+
+from pdf2image import convert_from_path
+
+
+
+
+def convert(pdf_path, output_dir, max_dim=1000):
+    images = convert_from_path(pdf_path, dpi=200)
+
+    for i, image in enumerate(images):
+        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/examples/extensions/pdf/skill/scripts/create_validation_image.py

@@ -1,37 +1,37 @@
-import json
-import sys
-
-from PIL import Image, ImageDraw
-
-
-
-
-def create_validation_image(page_number, fields_json_path, input_path, output_path):
-    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.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)
+import json
+import sys
+
+from PIL import Image, ImageDraw
+
+
+
+
+def create_validation_image(page_number, fields_json_path, input_path, output_path):
+    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.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/examples/extensions/pdf/skill/scripts/extract_form_field_info.py

@@ -1,122 +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])
+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])