SYMBOL INDEX (51 symbols across 19 files)

FILE: alignments/paragraph-level-summary-alignments/align_data_bi_encoder_paraphrase.py
  function merge_text_paragraphs (line 51) | def merge_text_paragraphs(paragraphs, min_sent=3, max_sent=12):
  function align_data_greedy_matching (line 96) | def align_data_greedy_matching(similarity_matrix):
  function align_data_stable_matching (line 106) | def align_data_stable_matching(similarity_matrix, text_capacity):
  function compute_similarities_bi_encoder (line 147) | def compute_similarities_bi_encoder(paragraphs, summaries):
  function gather_data (line 157) | def gather_data(alignments_bi_encoder_paraphrase, paragraphs, summaries,...
  function visualize_alignments (line 176) | def visualize_alignments(similarity_matrix, alignments, title, output_di...
  function aggregate_paragraph_summary_alignments (line 198) | def aggregate_paragraph_summary_alignments(examples):
  function main (line 229) | def main(args):

FILE: alignments/paragraph-level-summary-alignments/gather_data.py
  function fix_leftover_headers (line 22) | def fix_leftover_headers(summary_content):
  function fix_prefix_punctuation (line 40) | def fix_prefix_punctuation(summary_content):
  function fix_prefix_quotations (line 62) | def fix_prefix_quotations(summary_content):
  function fix_unclosed_quotations (line 92) | def fix_unclosed_quotations(summary_content):
  function fix_noncapitalized_prefix (line 113) | def fix_noncapitalized_prefix(summary_content):
  function fix_short_sentences (line 135) | def fix_short_sentences(summary_content):
  function main (line 171) | def main(args):

FILE: scripts/data_cleaning/clean_summaries.py
  function clean_summary (line 27) | def clean_summary(source):

FILE: scripts/data_cleaning/split_aggregate_chaps_all_sources.py
  function romanToInt (line 38) | def romanToInt(s):
  function save_separated_summaries (line 55) | def save_separated_summaries(separated_summaries, summary_json, summary_...
  function replace_pat2 (line 89) | def replace_pat2(matched_str):
  function separate_mulitple_summaries (line 105) | def separate_mulitple_summaries(summary_content, section_name_prefix, su...
  function remove_prefixes_line (line 189) | def remove_prefixes_line(line):
  function remove_prefixes_summary (line 235) | def remove_prefixes_summary(summary):

FILE: scripts/data_collection/bookwolf/get_summaries.py
  function get_overview_paragraphs (line 42) | def get_overview_paragraphs(overview_links, specific_summary_dir):
  function get_section_paragraphs (line 78) | def get_section_paragraphs(section_links, specific_summary_dir):

FILE: scripts/data_collection/bookwolf/get_works.py
  function scrape_index_pages (line 23) | def scrape_index_pages(seed_page):

FILE: scripts/data_collection/cliffnotes/get_summaries.py
  function wrap_data (line 32) | def wrap_data(name, summary, analysis, url):
  function scrape_section_continuation (line 41) | def scrape_section_continuation(parent_soup, section_header):

FILE: scripts/data_collection/cliffnotes/get_works.py
  function scrape_index_pages (line 22) | def scrape_index_pages(seed_page):

FILE: scripts/data_collection/gradesaver/get_works.py
  function scrape_index_pages (line 28) | def scrape_index_pages(seed_page):

FILE: scripts/data_collection/novelguide/get_summaries.py
  function hasNumbers (line 31) | def hasNumbers(inputString):
  function get_section_level_data (line 34) | def get_section_level_data(section_links):

FILE: scripts/data_collection/novelguide/get_works.py
  function scrape_index_pages (line 26) | def scrape_index_pages(seed_page):

FILE: scripts/data_collection/pinkmonkey/get_summaries.py
  function hasNumbers (line 37) | def hasNumbers(inputString):
  function chapter_section_check (line 40) | def chapter_section_check(link_text_lower, link_text_not_lower):
  function remove_toc (line 46) | def remove_toc(text):
  function get_overview_paragraphs (line 56) | def get_overview_paragraphs(overview, specific_summary_dir):
  function save_section_para (line 98) | def save_section_para(section_text, section_title, section_link, specifi...
  function get_section_paragraphs (line 113) | def get_section_paragraphs(page_url, specific_summary_dir):

FILE: scripts/data_collection/pinkmonkey/get_works.py
  function scrape_index_pages (line 26) | def scrape_index_pages(seed_page):

FILE: scripts/data_collection/shmoop/get_summaries.py
  function wrap_data (line 32) | def wrap_data(name, summary, analysis, url):
  function get_summary (line 41) | def get_summary(summary_infos):

FILE: scripts/data_collection/shmoop/get_works.py
  function generate_page_links (line 23) | def generate_page_links(base_url, category_name, max_pages):
  function scrape_index_pages (line 27) | def scrape_index_pages(links):

FILE: scripts/data_collection/sparknotes/get_summaries.py
  function wrap_data (line 30) | def wrap_data(name, summary, analysis, url):
  function get_summary (line 45) | def get_summary(summary_info):

FILE: scripts/data_collection/sparknotes/get_works.py
  function scrape_index_pages (line 24) | def scrape_index_pages(seed_page):

FILE: scripts/data_collection/thebestnotes/get_summaries.py
  function unify_title (line 40) | def unify_title(title):
  function get_overview_paragraphs (line 45) | def get_overview_paragraphs(overview):
  function get_section_paragraphs (line 89) | def get_section_paragraphs(section, section_titles, section_title_orig, ...
  function save_section_para (line 184) | def save_section_para(section_paragraphs, section_titles, section_title_...

FILE: scripts/data_collection/thebestnotes/get_works.py
  function scrape_index_pages (line 28) | def scrape_index_pages(seed_page):