def write_overall_word_counts(paras):
text = ''
for para in paras_without_shlokas(paras):
text += decoder.text_with_phrases(
in_para_allcontent.contentlist(para)) + ' '
word_counts = counter.count_significant_words(text)
write_wordcounts_as_csv('GitaBhashya-try-counts.csv', word_counts)
print("Wrote counts to GitaBhashya-try-counts.csv")
def test_link_is_encoded_as_phrase(self):
links_match = []
for para in paras_from('bookmark with link.docx'):
phrase_contents = in_para_allcontent.pick_contents\
(in_para_allcontent.contentlist(para), lambda x: x["type"] == "phrase")
for content in phrase_contents:
links_match.append(
matcher.match(in_para_phrase.content_regex, content))
self.assertAllAreOk(links_match)
def test_bookmark_is_encoded_as_anchor(self):
anchors_match = []
for para in paras_from('anchor.docx'):
anchor_contents = in_para_allcontent.pick_contents\
(in_para_allcontent.contentlist(para), lambda x: x['type'] == "anchor")
for content in anchor_contents:
anchors_match.append(
matcher.match(in_para_bookmark.content_regex, content))
self.assertAllAreOk(anchors_match)
def test_reference_is_encoded_as_external(self):
extrefs_match = []
for para in paras_from('externalref.docx'):
extref_contents = in_para_allcontent.pick_contents\
(in_para_allcontent.contentlist(para), lambda x: x["type"] == "extref")
for content in extref_contents:
extrefs_match.append(
matcher.match(in_para_externalref.content_regex, content))
self.assertAllAreOk(extrefs_match)
def test_link_to_html_is_encoded_as_phrase(self):
links_match = []
para_with_link = paras_from('link to html.docx')[0]
phrase_contents = in_para_allcontent.pick_contents\
(in_para_allcontent.contentlist(para_with_link), lambda x: x["type"] == "phrase")
for content in phrase_contents:
links_match.append(
matcher.match(in_para_phrase.content_regex, content))
self.assertAllAreOk(links_match)
def write_chapter_wordmap(paras):
chapter_texts = {}
for para in paras_without_shlokas(paras):
append(
chapter_texts, para['chapter'],
decoder.text_with_phrases(in_para_allcontent.contentlist(para)) +
' ')
chapter_word_counts = pd.DataFrame()
for chapter in chapter_texts:
word_counts = counter.count_significant_words(chapter_texts[chapter])
for count_pair in word_counts:
chapter_word_counts.at[count_pair[0], chapter] = count_pair[1]
counter.chapter_wordcounts_to_heatmap(chapter_word_counts)
chapter_word_counts.to_csv('GitaBhashya-try-chapmap.csv')
print("Wrote chapter-wise counts to GitaBhashya-try-chapmap.csv")
make_html_heatmap(chapter_word_counts, 'GitaBhashya-try-heatmap.html')