[WORK IN PROGRESS] little recipes I use in processing (mostly Greek) texts

recipes.py

### strip specific accents

def strip_accents(w):
    return unicodedata.normalize("NFC", "".join(
        ch
        for ch in unicodedata.normalize("NFD", w)
        if ch not in ["\u0300", "\u0301", "\u0342"]
    ))

  
### strip all diacritics

def strip_diacritics(w):
    return unicodedata.normalize("NFC", "".join(
        ch
        for ch in unicodedata.normalize("NFD", w)
        if unicodedata.category(ch) != "Mn"
    ))


### iterate over a file, line-by-line skipping blank lines and Python-style comments starting with #

with open(filename) as f:
    for line in f:
        row = line.split("#")[0].strip()
        if not row:
            continue
        ...

            
### override certain values with a dictionary
# if `s` is a key in the dictionary, it is replaced with the value otherwise it is passed through

s = OVERRIDES.get(s, s)


### process the lines of two files pair-wise

with open(filename1) as file1:
    with open(filename2) as file2:
        for line1, line2 in zip(file1, file2):
            ...