Files
dvc/dvc/pathspec_math.py
T
11d906ee51 dvc check-ignore command (#4282)
* Update some tests first

fix #3736

* first edition

* solve failure in Windows

* For Windows ci

* Some help ducuments issue.

* Update dvc/ignore.py

abspath

Co-authored-by: Ruslan Kuprieiev <[email protected]>

* Refactor with OutOfWorkSpaceError

* Solve a bug

* Update dvc/command/check_ignore.py

Co-authored-by: Jorge Orpinel <[email protected]>

* Update dvc/command/check_ignore.py

Co-authored-by: Jorge Orpinel <[email protected]>

* Update dvc/command/check_ignore.py

* Revert "Refactor with OutOfWorkSpaceError"

This reverts commit 27eec49ed67346c89157edea998b6b5fa81d88f5.

* Two change request

1. Argument `targets`'s description.
2. Error handling of `_get_normalize_path`

* Update dvc/main.py

Co-authored-by: Ruslan Kuprieiev <[email protected]>

* `check_ignore` now only accept one path a time

1. Add a new test for the out side repo cases
2. check ignore now only check one file not file lists

Co-authored-by: Ruslan Kuprieiev <[email protected]>
Co-authored-by: karajan1001 <[email protected]>
Co-authored-by: Jorge Orpinel <[email protected]>
2020-08-03 08:27:50 +03:00

94 lines
2.5 KiB
Python

# Path Specification Pattern Math
# Including changing base dir of path specification patterns and merging
# of two path specification patterns with different base
# All the operations follow the documents of `gitignore`
import os
from collections import namedtuple
from pathspec.util import normalize_file
from dvc.utils import relpath
PatternInfo = namedtuple("PatternInfo", ["patterns", "file_info"])
def _not_ignore(rule):
return (True, rule[1:]) if rule.startswith("!") else (False, rule)
def _is_comment(rule):
return rule.startswith("#")
def _remove_slash(rule):
if rule.startswith("\\"):
return rule[1:]
return rule
def _match_all_level(rule):
if rule[:-1].find("/") >= 0 and not rule.startswith("**/"):
if rule.startswith("/"):
rule = rule[1:]
return False, rule
if rule.startswith("**/"):
rule = rule[3:]
return True, rule
def change_rule(rule, rel):
rule = rule.strip()
if _is_comment(rule):
return rule
not_ignore, rule = _not_ignore(rule)
match_all, rule = _match_all_level(rule)
rule = _remove_slash(rule)
if not match_all:
rule = f"/{rule}"
else:
rule = f"/**/{rule}"
if not_ignore:
rule = f"!/{rel}{rule}"
else:
rule = f"/{rel}{rule}"
rule = normalize_file(rule)
return rule
def _change_dirname(dirname, pattern_list, new_dirname):
if new_dirname == dirname:
return pattern_list
rel = relpath(dirname, new_dirname)
if rel.startswith(".."):
raise ValueError("change dirname can only change to parent path")
return [
PatternInfo(change_rule(rule.patterns, rel), rule.file_info)
for rule in pattern_list
]
def merge_patterns(pattern_a, prefix_a, pattern_b, prefix_b):
"""
Merge two path specification patterns.
This implementation merge two path specification patterns on different
bases. It returns the longest common parent directory, and the patterns
based on this new base directory.
"""
if not pattern_a:
return pattern_b, prefix_b
elif not pattern_b:
return pattern_a, prefix_a
longest_common_dir = os.path.commonpath([prefix_a, prefix_b])
new_pattern_a = _change_dirname(prefix_a, pattern_a, longest_common_dir)
new_pattern_b = _change_dirname(prefix_b, pattern_b, longest_common_dir)
if len(prefix_a) <= len(prefix_b):
merged_pattern = new_pattern_a + new_pattern_b
else:
merged_pattern = new_pattern_b + new_pattern_a
return merged_pattern, longest_common_dir