third_party/mesa-migrating/gen_credits.py

"""This script is part of the generation process that produces the list of licenses in src/CREDITS.fuchsia."""
import json


def snip_string(text, prefix):
    lines = text.splitlines()
    for i, line in enumerate(lines):
        if line.startswith(prefix):
            return '\n'.join(lines[:i])
    return text


def remove_line(text, prefix):
    lines = text.splitlines()
    new_lines = [line for line in lines if not line.startswith(prefix)]
    return '\n'.join(new_lines)


def extract_data(filepath):
    """
  Loads a JSON file and extracts Name, Filepath, and Text from each object.

  Args:
    filepath: The path to the JSON file.

  Returns:
    A list of dictionaries, where each dictionary contains the extracted data
    for one object.
  """
    try:
        with open(filepath, 'r') as f:
            data = json.load(f)
    except FileNotFoundError:
        print(f"Error: File not found at {filepath}")
        return None
    except json.JSONDecodeError:
        print(f"Error: Invalid JSON format in {filepath}")
        return None

    extracted_data = []
    for item in data:
        filepath = item["Filepath"]
        if filepath in [
                "METADATA",
                "docs/license.rst",
                "src/compiler/nir/nir_intrinsics_c.py",
                "src/compiler/nir/nir_intrinsics_h.py",
                "src/compiler/nir/nir_intrinsics_indices_h.py",
                "src/imagination/csbgen/gen_pack_header.py",
                "src/intel/perf/gen_perf.py",
                "fuchsia-build/third_party/fuchsia-infra-bazel-rules/tests/examples/hello_world_cpp/meta/hello_death_test.cml",
        ]:
            continue
        current_extracted_data = []
        for classification in item["Classifications"]:
            name = classification["Name"]
            text = classification["Text"]
            if name == "Unclassified":
                continue

            text = remove_line(text, "#ifndef")
            text = remove_line(text, "#define")

            text = snip_string(text, "#include")
            text = snip_string(text, "import")
            text = snip_string(text, "struct")
            text = snip_string(text, "#ifdef")
            text = snip_string(text, "from")
            text = snip_string(text, "#  error")
            text = snip_string(text, r" * \file rogue")
            text = snip_string(text, "#pragma")
            text = snip_string(text, "static")
            text = snip_string(text, '"""Helper functions')
            text = snip_string(text, '# A BUILD file')
            text = snip_string(text, '# TODO')
            text = snip_string(text, 'def ')
            text = snip_string(text, 'exports_files')
            text = snip_string(text, 'load(')
            text = snip_string(text, 'min_shac_version')
            text = snip_string(text, '# Autogenerated')
            text = snip_string(text, "template <")
            text = snip_string(text, "# Leave this line")

            text = snip_string(text, "/* Only leaving the")

            current_extracted_data.append({
                "Name": name,
                "Filepath": filepath,
                "Text": text.strip()
            })
        if len(current_extracted_data) > 0:
            extracted_data.extend(current_extracted_data)
    return extracted_data


# Example usage:
filepath = "output-include-text.json"  # Replace with your actual file path
extracted_data = extract_data(filepath)

mymap = {}

for d in extracted_data:
    if d["Text"] not in mymap:
        mymap[d["Text"]] = {
            "Name": d["Name"],
            "Text": d["Text"],
            "Filepaths": []
        }
    mymap[d["Text"]]["Filepaths"].append(d["Filepath"])

# Open the file in write mode ('w')
file = open("CREDITS.fuchsia", "w")

for key, value in sorted(mymap.items(),
                         key=lambda item:
                         (item[1]['Name'].lower(), item[1]['Text'])):
    file.write("=============================\n")
    file.write("{}\n\n".format(value["Name"]))
    for f in value["Filepaths"]:
        file.write("-> File: {}\n".format(f))
    file.write("\n")
    file.write(value["Text"] + "\n\n")

file.close()

if extracted_data:
    print(f"Successfully extracted data from {len(extracted_data)} objects.")
    # Print the first 5 items as an example:
    for i in range(min(5, len(extracted_data))):
        print(f"Item {i+1}: {extracted_data[i]}")
        print("-" * 20)

    # You can now process the extracted_data list further as needed.