def checkPairs(text):
matches = findRegEx(r"\w+\s+(\([^)]+(:?\.\s+[A-Z]))", text) # non closing
matches += findRegEx(
r"(\w+\s*\([^)]+\(\s*\w+|\w+\s*\)\s*\(\s*\w+)", text
) # nested or subsequent parentheses
# matches += findRegEx( r'(\w\w+\(\w)' , text ) # no space before
# @todo: check that the line is not code : no +-/= in the same line
for match in matches:
print(match[0], "Possibly problem with parentheses: ", match[2].group(0), "")
matches = findRegEx(r"\s+(“[^”]+“|”\s*“)", text) # nested or subsequent “”
# nested or subsequent “”
matches += findRegEx(r"\s+(‘[^’]+‘|’\s*‘)", text)
for match in matches:
print(match[0], "Possibly problem with quotes: ", match[2].group(0), "")
def checkPlural(text):
matches = findRegEx(
r"\s+(?:[Aa]n?|[Aa]nother|[Ee]ach|[Ee]very)\s+(\w+[^uis'’]s)\s+", text
)
for match in matches:
replace = (
match[2].group(0).replace(match[2].group(1), match[2].group(1)[:-1], 1)
)
def checkSplitInfinitve(text):
matches = findRegEx(r"\sto (" + reAdv + r") (\w{4,})", text)
for match in matches:
if match[2].group(2) not in lstDeterminer + lstAdpos + lstConjunction + lstAdv:
replace = "to " + match[2].group(2) + " " + match[2].group(1)
print(
match[0],
"An adverb probably splits an infinitive expression.",
match[2].group(0),
replace,
)
def checkTeXmath(text):
result = ""
reFunction = r"(sin|cos|tan|log|min|max|exp)"
matches = findRegEx(
r"\\begin\{equation\}\s*\n\s*([^$]+?)\s*\n\s*\\end\{equation\}", text)
# matched = findRegEx(r'\s\$(\S[^$]+\S)\$\s', text)
for match in matches:
# print(match[2].group(1))
fun = re.search(r"(?:\s|[\(\)\*])" + reFunction, match[2].group(1))
if fun != None:
result += ' * WARN: use "\\{}" instead of "{}". (Equation ln. {})'.format(
fun.group(1), fun.group(1), match[0])
return result
def checkAbbreviations(text):
# todo: check if Acronym was only used once => suspicious!
dictionary = {}
corrections = []
spelling.read_acronyms(dictionary, DIC_DIR.joinpath("acronyms.md"))
foundAbbreviations = lstAcronyms + list(dictionary.keys())
matches = findRegEx(r"\s([A-Z][A-Z])\s", text)
for match in matches:
if match[2].group(1) not in foundAbbreviations:
print(
match[0],
"Found two character acronym, could be written in full words.",
match[2].group(0),
"",
)
foundAbbreviations.append(match[2].group(1))
matches = findRegEx(r"\s([A-Z]{3,5})\s(?!\(|“)", text)
desc = "Acronym '{}' was probably never introduced"
for match in matches:
if (
"(" + match[2].group(1) + ")" not in text
and match[2].group(1) not in foundAbbreviations
):
print("Line {}: {}.".format(match[0], desc.format(match[2].group(0))))
foundAbbreviations.append(match[2].group(1))
corrections.append(
Correction(
match[0],
match[1],
match[2].group(0),
"?",
desc.format(match[2].group(0)),
)
)
return corrections
def checkTeXheadings(text):
lstTeXHeading = [
"title",
"chapter",
"section",
"subsection",
"subsubsection",
"paragraph",
]
for heading in lstTeXHeading:
matches = findRegEx(r"\\" + heading + r"\{([^}]*?)\}", text)
for match in matches:
words = split2words(match[2].group(1))
for word in words:
if (len(word) > 3 and word[0].islower()
and word not in lstAdpos + lstDet + lstConjunction):
print("Lowercase letter in heading: ", match[2].group(1))
break