tglstemmer 0.1.0__py3-none-any.whl

tglstemmer/__init__.py

@@ -0,0 +1 @@
+"""A package for Tagalog word stemming."""

tglstemmer/helpers/affixes.py

@@ -0,0 +1,27 @@
+import os
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+
+
+def get_affixes(type, folder_path=None):
+    """Get list of affixes from file.
+
+    Args:
+            type (str): Type of affixes to get. Value can only be:
+                    - 'pre': Prefixes
+                    - 'in': Infixes
+                    - 'suf': Suffixes
+            folder_path (str, optional): Path to the folder containing .txt files of Tagalog affixes.
+
+    Returns:
+            list: A list of affixes of chosen type.
+    """
+    if folder_path is None:
+        folder_path = os.path.join(script_dir, "../resources/affixes/")
+    with open(os.path.join(folder_path, f"{type}fixes.txt")) as in_file:
+        return sorted([affix.strip() for affix in in_file], key=len)
+
+
+PREFIXES = get_affixes("pre")
+INFIXES = get_affixes("in")
+SUFFIXES = get_affixes("suf")

tglstemmer/helpers/alphabet.py

@@ -0,0 +1,2 @@
+VOWELS = set("aeiou")
+CONSONANTS = set("bcdfghjklmnpqrstvwxyz")

tglstemmer/helpers/manipulation.py

@@ -0,0 +1,39 @@
+from ..stem import Stem
+
+
+def replace_letter(token, index, letter):
+    """Replaces a letter in a token.
+
+    Args:
+            token (str): Word to be updated.
+            index (int): Index of the letter to be replaced.
+            letter (str): Letter used to replace.
+
+    Returns:
+            str: The updated word.
+    """
+    token_as_list = list(token)
+
+    token_as_list[index] = letter
+
+    return Stem("".join(token_as_list), **token.__dict__)
+
+
+def swap_letters(token, index1, index2):
+    """Swaps two letters in a token.
+
+    Args:
+            token (str): Word to be updated.
+            index1 (int): Index of the first letter to be swapped.
+            index2 (int): Index of the second letter to be swapped.
+
+    Returns:
+            str: The updated word.
+    """
+    token_as_list = list(token)
+
+    index1_letter = token_as_list[index1]
+    token_as_list[index1] = token_as_list[index2]
+    token_as_list[index2] = index1_letter
+
+    return Stem("".join(token_as_list), **token.__dict__)

tglstemmer/helpers/validation.py

@@ -0,0 +1,63 @@
+from .alphabet import CONSONANTS, VOWELS
+
+
+def is_valid(token, valid_words=None):
+    """Checks if token is valid against a list of words.
+
+    Args:
+        token (str): Any word to be tested.
+        valid_words (list): List of valid words. Defaults to None.
+
+    Returns:
+        str/bool: The token if token is valid, False otherwise.
+    """
+    if not valid_words:
+        return token
+
+    if token in valid_words:
+        return token
+
+    return False
+
+
+def is_acceptable(token):
+    """Checks if token is acceptable against certain acceptability conditions.
+
+    Args:
+        token (str): Any word to be tested.
+
+    Returns:
+        str/bool: The token if token is acceptable, False otherwise.
+    """
+    if is_vowel(token[0]):
+        if len(token) == 2 or (len(token) >= 3 and any(is_consonant(c) for c in token)):
+            return token
+    elif is_consonant(token[0]) and (
+        len(token) == 3 or (len(token) >= 4 and any(is_vowel(c) for c in token))
+    ):
+        return token
+    return False
+
+
+def is_vowel(*substring):
+    """Checks if a substring is a consonant.
+
+    Args:
+        *substring: Substrings to be tested.
+
+    Returns:
+        bool: True if substring is consonant, False otherwise.
+    """
+    return all(letter.lower() in VOWELS for letter in "".join(substring))
+
+
+def is_consonant(*substring):
+    """Checks if a substring is a consonant.
+
+    Args:
+        *substring: Substrings to be tested.
+
+    Returns:
+        bool: True if substring is consonant, False otherwise.
+    """
+    return all(letter.lower() in CONSONANTS for letter in "".join(substring))

tglstemmer/helpers/words.py

@@ -0,0 +1,17 @@
+import os
+
+script_dir = os.path.dirname(os.path.realpath(__file__))
+
+
+def get_words(file_path=None):
+    """Get list of words from a Tagalog word list txt file.
+
+    Args:
+            file_path (str, optional): Path to the Tagalog word lsit txt file. Defaults to '<script_dir>/../resources/tgl_wordlist.txt'.
+    Returns:
+            list: A list of words.
+    """
+    if file_path is None:
+        file_path = os.path.join(script_dir, "../resources/tgl_wordlist.txt")
+    with open(file_path) as in_file:
+        return [word.strip().lower() for word in in_file]

tglstemmer/resources/affixes/infixes.txt

@@ -0,0 +1,2 @@
+in
+um

tglstemmer/resources/affixes/prefixes.txt

@@ -0,0 +1,102 @@
+i
+ka
+ika
+pa
+pang
+pan
+pam
+pina
+ipa
+ipapa
+paka
+pakaka
+pana
+panana
+pama
+pamama
+pinaka
+pinakama
+ma
+mang
+man
+mam
+mina
+mai
+maii
+maka
+makaka
+makakapag
+makapa
+makapag
+na
+nang
+nan
+nam
+nai
+naii
+naka
+nakaka
+nakakapag
+nakapa
+nakapag
+napa
+napapa
+napaka
+napag
+sa
+sang
+san
+sam
+ni
+mag
+magka
+magkaka
+magpa
+magpapa
+nag
+nagka
+nagkaka
+nagpa
+nagpapa
+pag
+pagka
+pagkaka
+pagpa
+pagpapa
+pinag
+ipag
+ipinag
+pinagka
+pinagkaka
+ipinagka
+ipinagkaka
+tag
+tig
+may
+maki
+makipag
+makipagka
+makikipag
+makikipagka
+naki
+nakipag
+nakipagka
+nakikipag
+nakikipagka
+paki
+pakiki
+pakipag
+pakipagka
+pakikipag
+pakikipagka
+pala
+mala
+tiga
+tigapag
+taga
+tagapag
+sing
+sin
+sim
+kasing
+di-

tglstemmer/resources/affixes/suffixes.txt

@@ -0,0 +1,19 @@
+an
+in
+han
+hin
+nan
+anan
+nin
+anin
+ang
+ing
+ita
+ito
+dor
+syon
+siyon
+ng
+g
+'t
+'y