YogeLiu/TexTeller
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🔧 Fix all ruff typo errors & test CI/CD workflow (#109)

Browse Source 
* [chore] Fix ruff typo

* [robot] Fix welcome robot
This commit is contained in:
OleehyO
2025-04-21 13:52:16 +08:00
committed by GitHub
parent 4d3be22956
commit c8e08a22aa
9 changed files with 127 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
texteller/api/format.py
View File

@@ -19,8 +19,8 @@ TEXT_LINE_START = ""
COMMENT_LINE_START = "% "
# Opening and closing delimiters
OPENS = ['{', '(', '[']
CLOSES = ['}', ')', ']']
OPENS = ["{", "(", "["]
CLOSES = ["}", ")", "]"]
# Names of LaTeX verbatim environments
VERBATIMS = ["verbatim", "Verbatim", "lstlisting", "minted", "comment"]
@@ -138,7 +138,7 @@ class Pattern:
contains_env_end=ENV_END in s,
contains_item=ITEM in s,
contains_splitting=True,
contains_comment='%' in s,
contains_comment="%" in s,
)
else:
return cls(
@@ -146,7 +146,7 @@ class Pattern:
contains_env_end=False,
contains_item=False,
contains_splitting=False,
contains_comment='%' in s,
contains_comment="%" in s,
)
@@ -169,11 +169,11 @@ def find_comment_index(line: str, pattern: Pattern) -> Optional[int]:
in_command = False
for i, c in enumerate(line):
if c == '\\':
if c == "\\":
in_command = True
elif in_command and not c.isalpha():
in_command = False
elif c == '%' and not in_command:
elif c == "%" and not in_command:
return i
return None
@@ -390,10 +390,10 @@ def find_wrap_point(line: str, indent_length: int, args: Args) -> Optional[int]:
line_width += 1
if line_width > wrap_boundary and wrap_point is not None:
break
if c == ' ' and prev_char != '\\':
if c == " " and prev_char != "\\":
if after_char:
wrap_point = i
elif c != '%':
elif c != "%":
after_char = True
prev_char = c
@@ -483,8 +483,8 @@ def split_line(line: str, state: State, file: str, args: Args, logs: List[Log])
if not match:
return line, ""
prev = match.group('prev')
rest = match.group('env')
prev = match.group("prev")
rest = match.group("env")
if args.verbosity >= 3: # Trace level
logs.append(
@@ -517,8 +517,8 @@ def clean_text(text: str, args: Args) -> str:
text = RE_NEWLINES.sub(f"{LINE_END}{LINE_END}", text)
# Remove tabs if they shouldn't be used
if args.tabchar != '\t':
text = text.replace('\t', ' ' * args.tabsize)
if args.tabchar != "\t":
text = text.replace("\t", " " * args.tabsize)
# Remove trailing spaces
text = RE_TRAIL.sub(LINE_END, text)
@@ -577,7 +577,7 @@ def _format_latex(old_text: str, file: str, args: Args) -> Tuple[str, List[Log]]
new_text = ""
# Select the character used for indentation
indent_char = '\t' if args.tabchar == '\t' else ' '
indent_char = "\t" if args.tabchar == "\t" else " "
# Get any extra environments to be indented as lists
lists_begin = [f"\\begin{{{l}}}" for l in args.lists]

134
texteller/api/katex.py
View File

@@ -5,13 +5,13 @@ from .format import format_latex
def _rm_dollar_surr(content):
pattern = re.compile(r'\\[a-zA-Z]+\$.*?\$|\$.*?\$')
pattern = re.compile(r"\\[a-zA-Z]+\$.*?\$|\$.*?\$")
matches = pattern.findall(content)
for match in matches:
if not re.match(r'\\[a-zA-Z]+', match):
new_match = match.strip('$')
content = content.replace(match, ' ' + new_match + ' ')
if not re.match(r"\\[a-zA-Z]+", match):
new_match = match.strip("$")
content = content.replace(match, " " + new_match + " ")
return content
@@ -33,97 +33,97 @@ def to_katex(formula: str) -> str:
"""
res = formula
# remove mbox surrounding
res = change_all(res, r'\mbox ', r' ', r'{', r'}', r'', r'')
res = change_all(res, r'\mbox', r' ', r'{', r'}', r'', r'')
res = change_all(res, r"\mbox ", r" ", r"{", r"}", r"", r"")
res = change_all(res, r"\mbox", r" ", r"{", r"}", r"", r"")
# remove hbox surrounding
res = re.sub(r'\\hbox to ?-? ?\d+\.\d+(pt)?\{', r'\\hbox{', res)
res = change_all(res, r'\hbox', r' ', r'{', r'}', r'', r' ')
res = re.sub(r"\\hbox to ?-? ?\d+\.\d+(pt)?\{", r"\\hbox{", res)
res = change_all(res, r"\hbox", r" ", r"{", r"}", r"", r" ")
# remove raise surrounding
res = re.sub(r'\\raise ?-? ?\d+\.\d+(pt)?', r' ', res)
res = re.sub(r"\\raise ?-? ?\d+\.\d+(pt)?", r" ", res)
# remove makebox
res = re.sub(r'\\makebox ?\[\d+\.\d+(pt)?\]\{', r'\\makebox{', res)
res = change_all(res, r'\makebox', r' ', r'{', r'}', r'', r' ')
res = re.sub(r"\\makebox ?\[\d+\.\d+(pt)?\]\{", r"\\makebox{", res)
res = change_all(res, r"\makebox", r" ", r"{", r"}", r"", r" ")
# remove vbox surrounding, scalebox surrounding
res = re.sub(r'\\raisebox\{-? ?\d+\.\d+(pt)?\}\{', r'\\raisebox{', res)
res = re.sub(r'\\scalebox\{-? ?\d+\.\d+(pt)?\}\{', r'\\scalebox{', res)
res = change_all(res, r'\scalebox', r' ', r'{', r'}', r'', r' ')
res = change_all(res, r'\raisebox', r' ', r'{', r'}', r'', r' ')
res = change_all(res, r'\vbox', r' ', r'{', r'}', r'', r' ')
res = re.sub(r"\\raisebox\{-? ?\d+\.\d+(pt)?\}\{", r"\\raisebox{", res)
res = re.sub(r"\\scalebox\{-? ?\d+\.\d+(pt)?\}\{", r"\\scalebox{", res)
res = change_all(res, r"\scalebox", r" ", r"{", r"}", r"", r" ")
res = change_all(res, r"\raisebox", r" ", r"{", r"}", r"", r" ")
res = change_all(res, r"\vbox", r" ", r"{", r"}", r"", r" ")
origin_instructions = [
r'\Huge',
r'\huge',
r'\LARGE',
r'\Large',
r'\large',
r'\normalsize',
r'\small',
r'\footnotesize',
r'\tiny',
r"\Huge",
r"\huge",
r"\LARGE",
r"\Large",
r"\large",
r"\normalsize",
r"\small",
r"\footnotesize",
r"\tiny",
]
for old_ins, new_ins in zip(origin_instructions, origin_instructions):
res = change_all(res, old_ins, new_ins, r'$', r'$', '{', '}')
res = change_all(res, r'\mathbf', r'\bm', r'{', r'}', r'{', r'}')
res = change_all(res, r'\boldmath ', r'\bm', r'{', r'}', r'{', r'}')
res = change_all(res, r'\boldmath', r'\bm', r'{', r'}', r'{', r'}')
res = change_all(res, r'\boldmath ', r'\bm', r'$', r'$', r'{', r'}')
res = change_all(res, r'\boldmath', r'\bm', r'$', r'$', r'{', r'}')
res = change_all(res, r'\scriptsize', r'\scriptsize', r'$', r'$', r'{', r'}')
res = change_all(res, r'\emph', r'\textit', r'{', r'}', r'{', r'}')
res = change_all(res, r'\emph ', r'\textit', r'{', r'}', r'{', r'}')
res = change_all(res, old_ins, new_ins, r"$", r"$", "{", "}")
res = change_all(res, r"\mathbf", r"\bm", r"{", r"}", r"{", r"}")
res = change_all(res, r"\boldmath ", r"\bm", r"{", r"}", r"{", r"}")
res = change_all(res, r"\boldmath", r"\bm", r"{", r"}", r"{", r"}")
res = change_all(res, r"\boldmath ", r"\bm", r"$", r"$", r"{", r"}")
res = change_all(res, r"\boldmath", r"\bm", r"$", r"$", r"{", r"}")
res = change_all(res, r"\scriptsize", r"\scriptsize", r"$", r"$", r"{", r"}")
res = change_all(res, r"\emph", r"\textit", r"{", r"}", r"{", r"}")
res = change_all(res, r"\emph ", r"\textit", r"{", r"}", r"{", r"}")
# remove bold command
res = change_all(res, r'\bm', r' ', r'{', r'}', r'', r'')
res = change_all(res, r"\bm", r" ", r"{", r"}", r"", r"")
origin_instructions = [
r'\left',
r'\middle',
r'\right',
r'\big',
r'\Big',
r'\bigg',
r'\Bigg',
r'\bigl',
r'\Bigl',
r'\biggl',
r'\Biggl',
r'\bigm',
r'\Bigm',
r'\biggm',
r'\Biggm',
r'\bigr',
r'\Bigr',
r'\biggr',
r'\Biggr',
r"\left",
r"\middle",
r"\right",
r"\big",
r"\Big",
r"\bigg",
r"\Bigg",
r"\bigl",
r"\Bigl",
r"\biggl",
r"\Biggl",
r"\bigm",
r"\Bigm",
r"\biggm",
r"\Biggm",
r"\bigr",
r"\Bigr",
r"\biggr",
r"\Biggr",
]
for origin_ins in origin_instructions:
res = change_all(res, origin_ins, origin_ins, r'{', r'}', r'', r'')
res = change_all(res, origin_ins, origin_ins, r"{", r"}", r"", r"")
res = re.sub(r'\\\[(.*?)\\\]', r'\1\\newline', res)
res = re.sub(r"\\\[(.*?)\\\]", r"\1\\newline", res)
if res.endswith(r'\newline'):
if res.endswith(r"\newline"):
res = res[:-8]
# remove multiple spaces
res = re.sub(r'(\\,){1,}', ' ', res)
res = re.sub(r'(\\!){1,}', ' ', res)
res = re.sub(r'(\\;){1,}', ' ', res)
res = re.sub(r'(\\:){1,}', ' ', res)
res = re.sub(r'\\vspace\{.*?}', '', res)
res = re.sub(r"(\\,){1,}", " ", res)
res = re.sub(r"(\\!){1,}", " ", res)
res = re.sub(r"(\\;){1,}", " ", res)
res = re.sub(r"(\\:){1,}", " ", res)
res = re.sub(r"\\vspace\{.*?}", "", res)
# merge consecutive text
def merge_texts(match):
texts = match.group(0)
merged_content = ''.join(re.findall(r'\\text\{([^}]*)\}', texts))
return f'\\text{{{merged_content}}}'
merged_content = "".join(re.findall(r"\\text\{([^}]*)\}", texts))
return f"\\text{{{merged_content}}}"
res = re.sub(r'(\\text\{[^}]*\}\s*){2,}', merge_texts, res)
res = re.sub(r"(\\text\{[^}]*\}\s*){2,}", merge_texts, res)
res = res.replace(r'\bf ', '')
res = res.replace(r"\bf ", "")
res = _rm_dollar_surr(res)
# remove extra spaces (keeping only one)
res = re.sub(r' +', ' ', res)
res = re.sub(r" +", " ", res)
# format latex
res = res.strip()

2
texteller/models/__init__.py
View File

@@ -1,3 +1,3 @@
from .texteller import TexTeller
__all__ = ['TexTeller']
__all__ = ["TexTeller"]

4
texteller/utils/image.py
View File

@@ -41,7 +41,7 @@ def readimgs(image_paths: list[str]) -> list[np.ndarray]:
if image is None:
raise ValueError(f"Image at {path} could not be read.")
if image.dtype == np.uint16:
_logger.warning(f'Converting {path} to 8-bit, image may be lossy.')
_logger.warning(f"Converting {path} to 8-bit, image may be lossy.")
image = cv2.convertScaleAbs(image, alpha=(255.0 / 65535.0))
channels = 1 if len(image.shape) == 2 else image.shape[2]
@@ -112,7 +112,7 @@ def transform(images: List[Union[np.ndarray, Image.Image]]) -> List[torch.Tensor
assert IMG_CHANNELS == 1, "Only support grayscale images for now"
images = [
np.array(img.convert('RGB')) if isinstance(img, Image.Image) else img for img in images
np.array(img.convert("RGB")) if isinstance(img, Image.Image) else img for img in images
]
images = [trim_white_border(image) for image in images]
images = [general_transform_pipeline(image) for image in images]

8
texteller/utils/latex.py
View File

@@ -21,7 +21,7 @@ def _change(input_str, old_inst, new_inst, old_surr_l, old_surr_r, new_surr_l, n
j = start + 1
escaped = False
while j < n and count > 0:
if input_str[j] == '\\' and not escaped:
if input_str[j] == "\\" and not escaped:
escaped = True
j += 1
continue
@@ -71,10 +71,10 @@ def change_all(input_str, old_inst, new_inst, old_surr_l, old_surr_r, new_surr_l
for p in pos[::-1]:
res[p:] = list(
_change(
''.join(res[p:]), old_inst, new_inst, old_surr_l, old_surr_r, new_surr_l, new_surr_r
"".join(res[p:]), old_inst, new_inst, old_surr_l, old_surr_r, new_surr_l, new_surr_r
)
)
res = ''.join(res)
res = "".join(res)
return res
@@ -121,7 +121,7 @@ def add_newlines(latex_str: str) -> str:
# 4. Cleanup: Collapse multiple consecutive newlines into a single newline.
# This handles cases where the replacements above might have created \n\n.
processed_str = re.sub(r'\n{2,}', '\n', processed_str)
processed_str = re.sub(r"\n{2,}", "\n", processed_str)
# Remove leading/trailing whitespace (including potential single newlines
# at the very start/end resulting from the replacements) from the entire result.