def strip_string()

in src/sal/utils/qwen_math_parser.py [0:0]

• 81 lines of code
• 28 McCabe index (conditional complexity)

def strip_string(string, skip_unit=False):
    string = str(string).strip()
    # linebreaks
    string = string.replace("\n", "")

    # right "."
    string = string.rstrip(".")

    # remove inverse spaces
    # replace \\ with \
    string = string.replace("\\!", "")
    # string = string.replace("\\ ", "")
    # string = string.replace("\\\\", "\\")

    # matrix
    string = re.sub(r"\\begin\{array\}\{.*?\}", r"\\begin{pmatrix}", string)
    string = re.sub(r"\\end\{array\}", r"\\end{pmatrix}", string)
    string = string.replace("bmatrix", "pmatrix")

    # replace tfrac and dfrac with frac
    string = string.replace("tfrac", "frac")
    string = string.replace("dfrac", "frac")
    string = (
        string.replace("\\neq", "\\ne")
        .replace("\\leq", "\\le")
        .replace("\\geq", "\\ge")
    )

    # remove \left and \right
    string = string.replace("\\left", "")
    string = string.replace("\\right", "")
    string = string.replace("\\{", "{")
    string = string.replace("\\}", "}")

    # Remove unit: miles, dollars if after is not none
    _string = re.sub(r"\\text{.*?}$", "", string).strip()
    if _string != "" and _string != string:
        # print("Warning: unit not removed: '{}' -> '{}'".format(string, _string))
        string = _string

    if not skip_unit:
        # Remove unit: texts
        for _ in range(2):
            for unit_text in unit_texts:
                # use regex, the prefix should be either the start of the string or a non-alphanumeric character
                # the suffix should be either the end of the string or a non-alphanumeric character
                _string = re.sub(r"(^|\W)" + unit_text + r"($|\W)", r"\1\2", string)
                if _string != "":
                    string = _string

    # Remove circ (degrees)
    string = string.replace("^{\\circ}", "")
    string = string.replace("^\\circ", "")

    # remove dollar signs
    string = string.replace("\\$", "")
    string = string.replace("$", "")
    string = string.replace("\\(", "").replace("\\)", "")

    # convert word number to digit
    string = convert_word_number(string)

    # replace "\\text{...}" to "..."
    string = re.sub(r"\\text\{(.*?)\}", r"\1", string)
    for key in ["x=", "y=", "z=", "x\\in", "y\\in", "z\\in", "x\\to", "y\\to", "z\\to"]:
        string = string.replace(key, "")
    string = string.replace("\\emptyset", r"{}")
    string = string.replace("(-\\infty,\\infty)", "\\mathbb{R}")

    # remove percentage
    string = string.replace("\\%", "")
    string = string.replace("\%", "")
    string = string.replace("%", "")

    # " 0." equivalent to " ." and "{0." equivalent to "{." Alternatively, add "0" if "." is the start of the string
    string = string.replace(" .", " 0.")
    string = string.replace("{.", "{0.")

    # cdot
    # string = string.replace("\\cdot", "")
    if (
        string.startswith("{")
        and string.endswith("}")
        and string.isalnum()
        or string.startswith("(")
        and string.endswith(")")
        and string.isalnum()
        or string.startswith("[")
        and string.endswith("]")
        and string.isalnum()
    ):
        string = string[1:-1]

    # inf
    string = string.replace("infinity", "\\infty")
    if "\\infty" not in string:
        string = string.replace("inf", "\\infty")
    string = string.replace("+\\inity", "\\infty")

    # and
    string = string.replace("and", "")
    string = string.replace("\\mathbf", "")

    # use regex to remove \mbox{...}
    string = re.sub(r"\\mbox{.*?}", "", string)

    # quote
    string.replace("'", "")
    string.replace('"', "")

    # i, j
    if "j" in string and "i" not in string:
        string = string.replace("j", "i")

    # replace a.000b where b is not number or b is end, with ab, use regex
    string = re.sub(r"(\d+)\.0*([^\d])", r"\1\2", string)
    string = re.sub(r"(\d+)\.0*$", r"\1", string)

    # if empty, return empty string
    if len(string) == 0:
        return string
    if string[0] == ".":
        string = "0" + string

    # to consider: get rid of e.g. "k = " or "q = " at beginning
    if len(string.split("=")) == 2:
        if len(string.split("=")[0]) <= 2:
            string = string.split("=")[1]

    string = _fix_sqrt(string)
    string = string.replace(" ", "")

    # \frac1b or \frac12 --> \frac{1}{b} and \frac{1}{2}, etc. Even works with \frac1{72} (but not \frac{72}1). Also does a/b --> \\frac{a}{b}
    string = _fix_fracs(string)

    # NOTE: X/Y changed to \frac{X}{Y} in dataset, but in simple cases fix in case the model output is X/Y
    string = _fix_a_slash_b(string)

    return string