13566383609

Committed 27 Feb 2025 12:28PM UTC coverage: 96.402% (-1.9%) from 98.268%

Build # 13566383609

Build Type

push

github

Committed by

mbrsamsung

Commit Message

fix(example): update based on schema changes

Signed-off-by: Simon A. F. Lund <os@safl.dk>

Run Details

777 of 806 relevant lines covered (96.4%)

0.96 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

97.83

/src/senfd/cli.py

"""
Command-Line Interface
======================

Produces organized and semantically enriched ``.json`` documents from
"""

import json
from argparse import ArgumentParser, Namespace, RawTextHelpFormatter
from pathlib import Path
from typing import List

import senfd
import senfd.pipeline
import senfd.schemas
from senfd.documents import get_document_classes
from senfd.documents.base import to_file
from senfd.documents.merged import FromFolder
from senfd.errors import Error

PARSEARGS_EPILOG = """\
Senfd
=====

The --skip-figures flag specifies a path to a TOML file containing a list of
figures to be skipped during processing.

The TOML file must follow this format:

[[skip]]
regex = "^Decimal.and.Binary.Units$"
matches = 1
description = ""

[[skip]]
regex = "^Byte, Word, and Dword Relationships$"
matches = 1
description = ""


Each entry under [[skip]] consists of:
  - regex: A regular expression matching the figure description.
  - matches: The expected number of occurrences of this figure in the document.
  - description: An optional text field describing the reason for skipping.

This allows flexible and pattern-based skipping of figures during execution.
"""


def to_log_file(errors: List[Error], filename: str, output: Path) -> Path:
    content = json.dumps(
        [{"type": type(error).__name__, **error.model_dump()} for error in errors],
        indent=4,
    )

    return to_file(content, f"{filename}.error.log", output)


def parse_args() -> Namespace:
    """Return command-line arguments"""

    parser = ArgumentParser(
        description="Semantically organize and enrich figures",
        epilog=PARSEARGS_EPILOG,
        formatter_class=RawTextHelpFormatter,
    )
    parser.add_argument(
        "document", nargs="*", type=Path, help="path to one or more document(s)"
    )
    parser.add_argument(
        "--output",
        type=Path,
        help="directory where the output will be saved",
        default=Path("output"),
    )
    parser.add_argument(
        "--dump-schema",
        action="store_true",
        help="dump schema(s) and exit",
    )
    parser.add_argument(
        "--skip-figures",
        type=Path,
        help="Path to toml file that contains list of figure classifiers to skip",
    )
    parser.add_argument(
        "--version",
        action="store_true",
        help="print the version and exit",
    )
    args = parser.parse_args()
    if not args.document and not args.dump_schema and not args.version:
        parser.error("the following arguments are required: document")

    return args


def main() -> int:
    """Command-line entrypoint"""

    args = parse_args()
    args.output.mkdir(parents=True, exist_ok=True)

    if args.version:
        print(senfd.__version__)
        return 0

    if args.dump_schema:
        for docclass in get_document_classes():
            docclass.to_schema_file(args.output)
        return 0

    for count, path in enumerate(sorted(args.document), 1):
        args.output.mkdir(parents=True, exist_ok=True)

        errors = senfd.pipeline.process(path, args.output, args)
        to_log_file(errors, path.stem, args.output)

    if FromFolder.is_applicable(args.output):  # Merge ModelDocuments
        merged, errors = FromFolder.convert(args.output, args)
        merged.to_json_file(args.output / merged.json_filename())

    return 0


if __name__ == "__main__":
    main()

1	"""
2	Command-Line Interface
3	======================
4
5	Produces organized and semantically enriched ``.json`` documents from
6	"""
7
8	import json	1✔
9	from argparse import ArgumentParser, Namespace, RawTextHelpFormatter	1✔
10	from pathlib import Path	1✔
11	from typing import List	1✔
12
13	import senfd	1✔
14	import senfd.pipeline	1✔
15	import senfd.schemas	1✔
16	from senfd.documents import get_document_classes	1✔
17	from senfd.documents.base import to_file	1✔
18	from senfd.documents.merged import FromFolder	1✔
19	from senfd.errors import Error	1✔
20
21	PARSEARGS_EPILOG = """\	1✔
22	Senfd
23	=====
24
25	The --skip-figures flag specifies a path to a TOML file containing a list of
26	figures to be skipped during processing.
27
28	The TOML file must follow this format:
29
30	[[skip]]
31	regex = "^Decimal.and.Binary.Units$"
32	matches = 1
33	description = ""
34
35	[[skip]]
36	regex = "^Byte, Word, and Dword Relationships$"
37	matches = 1
38	description = ""
39
40
41	Each entry under [[skip]] consists of:
42	- regex: A regular expression matching the figure description.
43	- matches: The expected number of occurrences of this figure in the document.
44	- description: An optional text field describing the reason for skipping.
45
46	This allows flexible and pattern-based skipping of figures during execution.
47	"""
48
49
50	def to_log_file(errors: List[Error], filename: str, output: Path) -> Path:	1✔
51	content = json.dumps(	1✔
52	[{"type": type(error).__name__, **error.model_dump()} for error in errors],
53	indent=4,
54	)
55
56	return to_file(content, f"{filename}.error.log", output)	1✔
57
58
59	def parse_args() -> Namespace:	1✔
60	"""Return command-line arguments"""
61
62	parser = ArgumentParser(	1✔
63	description="Semantically organize and enrich figures",
64	epilog=PARSEARGS_EPILOG,
65	formatter_class=RawTextHelpFormatter,
66	)
67	parser.add_argument(	1✔
68	"document", nargs="*", type=Path, help="path to one or more document(s)"
69	)
70	parser.add_argument(	1✔
71	"--output",
72	type=Path,
73	help="directory where the output will be saved",
74	default=Path("output"),
75	)
76	parser.add_argument(	1✔
77	"--dump-schema",
78	action="store_true",
79	help="dump schema(s) and exit",
80	)
81	parser.add_argument(	1✔
82	"--skip-figures",
83	type=Path,
84	help="Path to toml file that contains list of figure classifiers to skip",
85	)
86	parser.add_argument(	1✔
87	"--version",
88	action="store_true",
89	help="print the version and exit",
90	)
91	args = parser.parse_args()	1✔
92	if not args.document and not args.dump_schema and not args.version:	1✔
93	parser.error("the following arguments are required: document")	1✔
94
95	return args	1✔
96
97
98	def main() -> int:	1✔
99	"""Command-line entrypoint"""
100
101	args = parse_args()	1✔
102	args.output.mkdir(parents=True, exist_ok=True)	1✔
103
104	if args.version:	1✔
105	print(senfd.__version__)	1✔
106	return 0	1✔
107
108	if args.dump_schema:	1✔
109	for docclass in get_document_classes():	1✔
110	docclass.to_schema_file(args.output)	1✔
111	return 0	1✔
112
113	for count, path in enumerate(sorted(args.document), 1):	1✔
114	args.output.mkdir(parents=True, exist_ok=True)	1✔
115
116	errors = senfd.pipeline.process(path, args.output, args)	1✔
117	to_log_file(errors, path.stem, args.output)	1✔
118
119	if FromFolder.is_applicable(args.output): # Merge ModelDocuments	1✔
120	merged, errors = FromFolder.convert(args.output, args)	1✔
121	merged.to_json_file(args.output / merged.json_filename())	1✔
122
123	return 0	1✔
124
125
126	if __name__ == "__main__":	1✔
127	main()	×

safl / senfd / 13566383609

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous