python/src/server/services/search/dictionaries/stop_words.py

"""
Stop words for keyword extraction.
"""

# Common stop words to filter out
STOP_WORDS = {
    "a",
    "an",
    "and",
    "are",
    "as",
    "at",
    "be",
    "been",
    "by",
    "for",
    "from",
    "has",
    "have",
    "he",
    "in",
    "is",
    "it",
    "its",
    "of",
    "on",
    "that",
    "the",
    "to",
    "was",
    "will",
    "with",
    "what",
    "when",
    "where",
    "which",
    "who",
    "why",
    "how",
    "can",
    "could",
    "should",
    "would",
    "may",
    "might",
    "must",
    "shall",
    "do",
    "does",
    "did",
    "done",
    "this",
    "these",
    "those",
    "there",
    "their",
    "them",
    "they",
    "we",
    "you",
    "your",
    "our",
    "us",
    "am",
    "im",
    "me",
    "my",
    "i",
    "if",
    "so",
    "or",
    "but",
    "not",
    "no",
    "yes",
}

# Technical stop words that are too common in code/docs to be useful
TECHNICAL_STOP_WORDS = {
    "get",
    "set",
    "use",
    "using",
    "used",
    "make",
    "made",
    "create",
    "created",
    "add",
    "added",
    "remove",
    "removed",
    "update",
    "updated",
    "delete",
    "deleted",
    "need",
    "needs",
    "want",
    "wants",
    "like",
    "example",
    "examples",
    "please",
    "help",
    "show",
    "find",
    "search",
    "look",
    "looking",
    "implement",
    "implementing",
    "implemented",
    "implementation",
}