Das deutsche Python-Forum

Code: Alles auswählen

def substitute_with_rhymes(investigated_sayings):
    for key, value in investigated_sayings.items():
        for word in value:
            substituted_word = get_rhyme(word)
            if substituted_word:
                yield key.replace(word, substituted_word)


def show_sayings(sayings):
    for saying in sayings:
        print(saying)
#    print(f"Anzahl {len(sayings)}")

Code: Alles auswählen

saying, seperator, _ = line[1:].partition('."')

Code: Alles auswählen

root, *_ = Path().absolute().parts

Code: Alles auswählen

In[2]:3 +2
Out[2]: 5
In[3]:_
Out[3]: 5

Code: Alles auswählen

def investigate_sayings():
    # TODO
    # Verbesserung mittels wiki-api - Texte direkt aus Wikipedia "Sprichwörter" auslesen?
    # Tutorials:
    #  - https://wdqs-tutorial.toolforge.org/index.php/simple-queries/the-simplest-query/basic-sparql-query/
    #  - https://docs.python.org/3/howto/logging.html#logging-basic-tutorial
    # Methode "tut" zu viel - Zerlegen in Beschaffung der Daten und Erstellen des Datenmodells
    filename_sayings = Path("Daten/WortspielGenerator/Sprueche_raw.txt")

    path_log = Path("Daten/WortspielGenerator/logs/")
    path_log.mkdir(parents=True, exist_ok=True)
    filename_log = Path("Daten/WortspielGenerator/logs/Sprueche_ausgemustert.txt")

    logging.basicConfig(filename=str(filename_log), level=logging.DEBUG)
    with open(filename_sayings, "r", encoding="UTF-8") as file:
        investigated_sayings = defaultdict(list)
        for line_number, line in enumerate(file, 1):
            if line.startswith('"'):
                saying, seperator, _ = line[1:].partition('"')
                if seperator:
                    for word in saying.split():
                        if word.istitle():
                            investigated_sayings[saying].append(word)
                else:
                    logging.debug(f"Fehler: Ende von Spruch in Zeile {line_number} nicht gefunden: {line.strip()}")
            else:
                line = line.rstrip()
                if not (len(line) == 1 and line.isalpha()):
                    logging.debug(f"Fehler: Unerwartete(s) Zeichen in Zeile {line_number}: {line}.")
        return investigated_sayings

Code: Alles auswählen

def investigate_sayings_alternative():
    # TODO
    # Verbesserung mittels wiki-api - Texte direkt aus Wikipedia "Sprichwörter" auslesen?
    # Tutorials:
    #  - https://wdqs-tutorial.toolforge.org/index.php/simple-queries/the-simplest-query/basic-sparql-query/
    #  - https://docs.python.org/3/howto/logging.html#logging-basic-tutorial
    # Methode "tut" zu viel - Zerlegen in Beschaffung der Daten und Erstellen des Datenmodells
    filename_sayings = Path("Daten/WortspielGenerator/Sprueche_raw.txt")

    path_log = Path("Daten/WortspielGenerator/logs/")
    path_log.mkdir(parents=True, exist_ok=True)
    filename_log = Path("Daten/WortspielGenerator/logs/Sprueche_ausgemustert.txt")

    with open(filename_sayings, "r", encoding="UTF-8") as file:
        investigated_sayings = defaultdict(list)
        for line_number, line in enumerate(file, 1):
            investigate_saying(line, line_number, filename_log, investigated_sayings)
        return investigated_sayings


def investigate_saying(line, line_number, filename_log, investigated_sayings):
    logging.basicConfig(filename=str(filename_log), level=logging.DEBUG)
    if line.startswith('"'):
        saying, seperator, _ = line[1:].partition('"')
        if seperator:
            for word in saying.split():
                if word.istitle():
                    investigated_sayings[saying].append(word)
        else:
            logging.debug(f"Fehler: Ende von Spruch in Zeile {line_number} nicht gefunden: {line.strip()}")
    else:
        line = line.rstrip()
        if not (len(line) == 1 and line.isalpha()):
            logging.debug(f"Fehler: Unerwartete(s) Zeichen in Zeile {line_number}: {line}.")

Code: Alles auswählen

import logging
from pathlib impot Path
logger = logging.getLogger(__name__)

LOG_FILENAME = Path("Daten/WortspielGenerator/logs/Sprueche_ausgemustert.txt")

def initialize_logging():
    LOG_FILENAME.parent.mkdir(parents=True, exist_ok=True)
    logging.basicConfig(filename=LOG_FILENAME, level=logging.DEBUG)

def investigate_sayings(filename):
    with filename.open(encoding="UTF-8") as file:
        sayings = defaultdict(list)
        for line_number, line in enumerate(file, 1):
            if line.startswith('"'):
                saying, seperator, _ = line[1:].partition('"')
                if seperator:
                    for word in saying.split():
                        if word.istitle():
                            sayings[saying].append(word)
                else:
                    logger.error(f"Fehler: Ende von Spruch in Zeile {line_number} nicht gefunden: {line.strip()}")
            else:
                line = line.rstrip()
                if not (len(line) == 1 and line.isalpha()):
                    logger.error(f"Fehler: Unerwartete(s) Zeichen in Zeile {line_number}: {line}.")
    return sayings


def main():
    initialize_logging()
    filename_sayings = Path("Daten/WortspielGenerator/Sprueche_raw.txt")
    sayings = investigated_sayings(filename_sayings)
    ...

Code: Alles auswählen

def read_sayings(filename):
    with filename.open(encoding="UTF-8") as file:
        for line_number, line in enumerate(file, 1):
            if line.startswith('"'):
                saying, seperator, _ = line[1:].partition('"')
                if seperator:
                    yield saying
                else:
                    logger.error(f"Fehler: Ende von Spruch in Zeile {line_number} nicht gefunden: {line.strip()}")
            else:
                line = line.rstrip()
                if not (len(line) == 1 and line.isalpha()):
                    logger.error(f"Fehler: Unerwartete(s) Zeichen in Zeile {line_number}: {line}.")

def investigate_sayings(filename):
    sayings = defaultdict(list)
    for saying in read_sayings(filename):
        for word in saying.split():
            if word.istitle():
                sayings[saying].append(word)
    return sayings