Spacy German address patterns

spacy_german_address_patterns.py

# Goal: Fetch German street addresses
# Works on: 
# Müllerstr. 26
# Müllerstr 26
# Müllerstraße
# Müllerstraße 26
# Müllerplatz
# Müllerstraße 26a
# Müller Straße 26

# 2 versions:
# 1) multiple patterns
# 2) one pattern

# weird: Is the housenumber at the end of a sentence, Spacy adds the punct to the token. 
# So that punct needs to be considered as well
street_labels = ".*(platz|[Ss]tra[ssß]e|str)$"



patterns = [
    {"label": "ADR", 
     "pattern": [
         {"TEXT": {"REGEX": street_labels}}, 
         # here might be a punct or not: Müllerstr. 26 or Müllerstr 26
         {"IS_PUNCT": True, "OP": "?"}, 
         # house number can have several formats: 2, 26, 266, 2a, 22a, 222a, 
         # last six ones catch cases at end of sentence. there might be a better solution out there... 
         {"SHAPE": {"IN": ["d", "dd", "ddd", "dddx", "ddx", "dx", "d.", "dd.", "ddd.", "dx.", "ddx.", "dddx."]}, "OP": "?"}
     ]},
    # if street name has to parts: Müller Straße
     {"label": "ADR", 
      "pattern": [
          {"SHAPE": "Xxxxx", "OP": "?"}, 
          {"TEXT": "Straße"}, 
          {"IS_PUNCT": True, "OP": "?"}, 
          {"SHAPE": {"IN": ["d", "dd", "ddd", "dddx", "ddx", "dx", "d.", "dd.", "ddd."]}, "OP": "?"}
      ]}
    ]


# as multiple patterns

patterns = [
    # Müllerstraße 26. (with punct at the end!)
    {"label": "ADR", "pattern": [{"TEXT": {"REGEX": street_labels}}, {"SHAPE": {"IN": ["d.", "dd.", "ddd."]}}]},
    # Müllerstr. 26
    {"label": "ADR", "pattern": [{"TEXT": {"REGEX": street_labels}}, {"IS_PUNCT": True, "OP": "?"}, {"IS_DIGIT": True}]},
    # Müllerstra0e 10a
    {"label": "ADR", "pattern": [{"TEXT": {"REGEX": street_labels}}, {"IS_PUNCT": True, "OP": "?"}, {"SHAPE": {"IN": ["dddx", "ddx", "dx"]}}]},
    # Müller Straße 23
    {"label": "ADR", "pattern": [{"SHAPE": "Xxxxx"}, {"TEXT": {"REGEX": street_labels}}, {"IS_DIGIT": True, "OP": "?"}]},
    # Müllerstraße 26
    {"label": "ADR", "pattern": [{"TEXT": {"REGEX": street_labels}}, {"IS_DIGIT": True}]},
    # Müllerstraße or Odeonsplatz    
    {"label": "ADR", "pattern": [{"TEXT": {"REGEX": street_labels}}]},
    ]

https://ner.pythonhumanities.com/02_01_spaCy_Entity_Ruler.html

https://stackoverflow.com/questions/66821133/creating-rule-based-matching-with-spacy-and-python-for-detecting-addresses/71605720#71605720