Last active
May 7, 2024 18:30
-
-
Save vergenzt/154fa174175432c16c0c106ed4453222 to your computer and use it in GitHub Desktop.
Parse Python requirements files into AST JSON representation via tree-sitter-requirements
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env pip-run | |
""" | |
Parse Python requirements files into AST JSON representation | |
""" | |
# /// script | |
# dependencies = ['tree-sitter-requirements'] | |
# /// | |
import json | |
import sys | |
from subprocess import check_output | |
from typing import Iterator, Tuple, Union | |
import tree_sitter_requirements as reqs | |
from tree_sitter import TreeCursor | |
# https://jqlang.github.io/jq/manual/#streaming | |
JSONValue = Union[None, bool, str, int, dict, list] | |
JSONPathItem = Union[int, str] | |
JSONPath = Tuple[JSONPathItem, ...] | |
JSONItem = Tuple[JSONPath, JSONValue] | |
JSONClose = Tuple[JSONPath] | |
JSONStream = Iterator[Union[JSONItem, JSONClose]] | |
def json_stream(cursor: TreeCursor, ctx: JSONPath = ()) -> JSONStream: | |
i = 0 | |
yield ((*ctx, "type"), cursor.node.type) | |
yield ((*ctx, "text"), cursor.node.text.decode()) | |
if fn := cursor.field_name: | |
yield ((*ctx, "field"), fn) | |
if cursor.goto_first_child(): | |
i = 0 | |
while True: | |
yield from json_stream(cursor, (*ctx, "_", i)) | |
if not cursor.goto_next_sibling(): | |
break | |
i += 1 | |
yield ((*ctx, "_"),) | |
assert cursor.goto_parent() | |
yield (ctx,) | |
tree = reqs.parse(sys.stdin.read()) | |
stream = json_stream(tree.walk()) | |
stream_text = json.dumps(list(stream)) | |
stream_json = check_output(["jq", "fromstream(.[])"], input=stream_text, text=True) | |
print(stream_json) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment