From 4d534fd0396330e47b2acc442cc8983f65c0e4d0 Mon Sep 17 00:00:00 2001
From: Thomas Huber <thomas.huber@unisg.ch>
Date: Wed, 30 Oct 2024 10:48:58 +0100
Subject: [PATCH 1/2] adds number_of_n_syllable_words_all function, to count
 all frequencies of all numbers of syllables found in texts

---
 README.md                         |  1 +
 linguaf/descriptive_statistics.py | 34 ++++++++++++++++++++++---------
 2 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index 5f65916..1e32ab6 100644
--- a/README.md
+++ b/README.md
@@ -27,6 +27,7 @@ The following descriptive statistics are supported (`descriptive_statistics.py`
 * Number of syllables `syllable_count`
 * Number of sentences `sentence_count`
 * Number of n-syllable words `number_of_n_syllable_words`
+* Number of n-syllable words for all found syllables `number_of_n_syllable_words_all`
 * Average syllables per word `avg_syllable_per_word`
 * Average word length `avg_word_length`
 * Average sentence length `avg_sentence_length`
diff --git a/linguaf/descriptive_statistics.py b/linguaf/descriptive_statistics.py
index a9e3613..39b9a6d 100644
--- a/linguaf/descriptive_statistics.py
+++ b/linguaf/descriptive_statistics.py
@@ -15,7 +15,6 @@
 from linguaf import SUPPORTED_LANGS, __load_json, __check_bool_param, __check_documents_param, __check_lang_param, \
     __check_text_param, __check_words_param
 
-
 LOGGER = logging.getLogger(__name__)
 
 try:
@@ -28,7 +27,6 @@
 PUNCTUATION = r"""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~—«»"""
 STOPWORDS = dict()
 
-
 for language in SUPPORTED_LANGS:
     try:
         # TODO: consider using nltk directly
@@ -171,25 +169,41 @@ def number_of_n_syllable_words(documents: list, lang: str = 'en', n: tuple = (1,
     __check_documents_param(documents)
     __check_lang_param(lang)
 
+    counts = number_of_n_syllable_words_all(documents, lang, remove_stopwords)
+    count = 0
+    for i in range(n[0], n[1]):
+        count += counts.get(i, 0)
+    return count
+
+
+def number_of_n_syllable_words_all(documents: list, lang: str = 'en', remove_stopwords: bool = False) -> dict:
+    """Count each found number of syllables in a list of words.
+
+    Keyword arguments:
+    documents -- the list of documents
+    lang -- language of the words
+    """
+    __check_documents_param(documents)
+    __check_lang_param(lang)
+
     # TODO: refactor duplicate code!
     unsupported_langs = ['zh', 'hy']
     if lang in unsupported_langs:
         raise ValueError(f"Syllable counting is currently not supported for the language " + lang + "!")
         # TODO: chinese does have syllables! so this should be supported eventually
-        # however, chinese does not support hyphenation, so the implementation below does not work for it! 
+        # however, chinese does not support hyphenation, so the implementation below does not work for it!
 
     words = get_words(documents, lang, remove_stopwords)
-    if n[0] < 1 or n[1] <= n[0]:
-        raise ValueError(f"The given n parameter isn't correct: {n}. n=tuple(x,y), x>0, y>x.")
 
-    count = 0
+    counts = {}
     dic = pyphen.Pyphen(lang=lang)  # TODO: match language
     for word in words:
         syl_cnt = len(dic.inserted(word).split('-'))
-        for i in range(n[0], n[1]):
-            if syl_cnt == i:
-                count += 1
-    return count
+        if syl_cnt in counts:
+            counts[syl_cnt] += 1
+        else:
+            counts[syl_cnt] = 1
+    return counts
 
 
 def get_words(documents: list, lang: str = 'en', remove_stopwords: bool = False) -> list:

From cb553c2e038eeaabc8a877b3adda9f494a033c3e Mon Sep 17 00:00:00 2001
From: Thomas Huber <thomas.huber@unisg.ch>
Date: Wed, 30 Oct 2024 11:11:06 +0100
Subject: [PATCH 2/2] using defaultdict instead of regular dict

---
 linguaf/descriptive_statistics.py | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/linguaf/descriptive_statistics.py b/linguaf/descriptive_statistics.py
index 39b9a6d..8f8f76c 100644
--- a/linguaf/descriptive_statistics.py
+++ b/linguaf/descriptive_statistics.py
@@ -195,14 +195,11 @@ def number_of_n_syllable_words_all(documents: list, lang: str = 'en', remove_sto
 
     words = get_words(documents, lang, remove_stopwords)
 
-    counts = {}
+    counts = collections.defaultdict(int)
     dic = pyphen.Pyphen(lang=lang)  # TODO: match language
     for word in words:
         syl_cnt = len(dic.inserted(word).split('-'))
-        if syl_cnt in counts:
-            counts[syl_cnt] += 1
-        else:
-            counts[syl_cnt] = 1
+        counts[syl_cnt] += 1
     return counts