count_loc.py

import textwrap
import subprocess
import json
from pathlib import Path

## Configuration ##

# All langs except real_langs will be ignored
only_include_langs = {"C++", "C", "C Header", "C++ Header", "YAML", "Makefile", "Markdown", "Shell", "CMake", "Python", "Dockerfile"}

exclude_files = set(map(Path, [
    "open_vins",
]))

# This is the column to use to weight complexity of the whole project by its components
weight_column = "Lines"
# These are the valid choices
assert weight_column in {"Bytes", "CodeBytes", "Lines", "Code", "Comment", "Blank", "Complexity", "Count", "WeightedComplexity"}

## End of configuration ##

def scc(list_of_paths):
    proc = subprocess.run(["scc", "--format=json", *map(str, list_of_paths)], capture_output=True, text=True, check=True)
    return json.loads(proc.stdout)

def fd(path, type_=None, max_depth=None):
    args = []
    if type_ is not None:
        args.append(f"--type={type_}")
    if max_depth is not None:
        args.append(f"--max-depth={max_depth}")
    proc = subprocess.run(["fd", *args, ".", str(path)], capture_output=True, text=True, check=True)
    return [Path(path) for path in proc.stdout.split("\n") if path != "." and path]

all_langs = set()
breakdown = dict()

def process(component, file_):
    breakdown[component] = dict()
    if isinstance(file_, list):
        files = file_
    else:
        files = fd(file_, type_="file")
    for file_ in files:
        breakdown[component][file_] = {}
        for block in scc([file_]):
            all_langs.add(block["Name"])
            if block["Name"] in only_include_langs:
                breakdown[component][file_][block["Name"]] = block

root_files = []
for file_ in fd(".", max_depth=1):
    if file_ in exclude_files:
        pass
    elif file_.is_symlink():
        pass
    elif file_.is_dir():
        process(str(file_), file_)
    else:
        root_files.append(file_)
process(".", root_files)

def shorten(string, width):
    if len(string) > width:
        cut = int(width * 0.6)
        assert width > 3
        rest = width - cut - 3
        return string[:cut] + "..." + string[-rest:]
    else:
        return string

print("Excluding langs: " + ", ".join(all_langs - only_include_langs))

print("Individual:")
print(f"{'component':<20s} {'path':<40s} {'language':<10s} {'lines':>6s} {'bytes':>6s} {'complx':>6s}")
for component, files in breakdown.items():
    lines = sum(block["Lines"] for blocks in files.values() for block in blocks.values())
    complexity = sum(block["Complexity"] for blocks in files.values() for block in blocks.values())
    blank = ""
    n_files = str(len(files))
    # print(f"{component:<20s} {n_files:<4s} {blank:46s} {lines: 5d} {complexity: 4d}")
    for file_, blocks in files.items():
        file_str = shorten(str(file_), width=40)
        for lang, block in blocks.items():
            print(f"{component:<20s} {file_str:<40s} {lang:<10s} {block['Lines']: 6d} {block['Bytes']: 6d} {block['Complexity']: 6d}")

print()
print("Aggregated by component:")
print(f"{'component':<20s} {'path':<40s} {'':<10s} {'lines':<6s} {'bytes':>6s} {'complx':>6s}")
for component, files in breakdown.items():
    lines = sum(block["Lines"] for blocks in files.values() for block in blocks.values())
    complexity = sum(block["Complexity"] for blocks in files.values() for block in blocks.values())
    bytes_ = sum(block["Bytes"] for blocks in files.values() for block in blocks.values())
    blank = ""
    n_files = str(len(files))
    print(f"{component:<20s} {n_files:<4s} {blank:46s} {lines: 6d} {bytes_: 6d} {complexity: 6d}")
lines = sum(block["Lines"] for files in breakdown.values() for blocks in files.values() for block in blocks.values())
complexity = sum(block["Complexity"] for files in breakdown.values() for blocks in files.values() for block in blocks.values())
bytes_ = sum(block["Bytes"] for files in breakdown.values() for blocks in files.values() for block in blocks.values())
n_files = str(sum(len(files) for files in breakdown.values()))
component = 'all'
print(f"{component:<20s} {n_files:<4s} {blank:46s} {lines: 6d} {bytes_: 6d} {complexity: 6d}")

print()
print("Aggregated by component (CSV):")
print(f"{'component'},{'path'},{'lines'},{'bytes'},{'complx'}")
for component, files in breakdown.items():
    lines = sum(block["Lines"] for blocks in files.values() for block in blocks.values())
    complexity = sum(block["Complexity"] for blocks in files.values() for block in blocks.values())
    bytes_ = sum(block["Bytes"] for blocks in files.values() for block in blocks.values())
    blank = ""
    n_files = str(len(files))
    print(f"{component},{n_files},{blank},{lines},{bytes_},{complexity}")
lines = sum(block["Lines"] for files in breakdown.values() for blocks in files.values() for block in blocks.values())
complexity = sum(block["Complexity"] for files in breakdown.values() for blocks in files.values() for block in blocks.values())
bytes_ = sum(block["Bytes"] for files in breakdown.values() for blocks in files.values() for block in blocks.values())
n_files = str(sum(len(files) for files in breakdown.values()))
component = 'all'
print(f"{component},{n_files},{blank},{lines},{bytes_},{complexity}")