List of all items

Structs

• chunking::Chunk
• chunking::ChunkerConfig
• chunking::ChunkerResult
• chunking::TextChunker
• clean_text::TextCleaner
• splitting::TextSplit
• splitting::TextSplitter
• test_text::Chunking
• test_text::ChunkingTestCase
• test_text::ChunkingTestCases
• test_text::Splitting
• test_text::Text
• test_text::chunking_small
• test_text::chunking_tiny
• test_text::graphemes_unicode
• test_text::html_short
• test_text::joining
• test_text::long
• test_text::many_subjects
• test_text::medium
• test_text::one_subject_many_topics
• test_text::one_subject_one_topic
• test_text::really_long
• test_text::sentences_rule_1
• test_text::sentences_rule_2
• test_text::sentences_rule_3
• test_text::sentences_rule_4
• test_text::sentences_unicode
• test_text::single_eol
• test_text::small
• test_text::smollest
• test_text::tiny
• test_text::two_plus_eol
• test_text::words_unicode

Enums

• clean_text::Newlines
• concatenator::TextConcatenator
• splitting::Separator
• splitting::SeparatorGroup

Traits

• concatenator::TextConcatenatorTrait

Functions

• chunking::chunk_text
• clean_html::clean_html
• clean_text::normalize_whitespace
• clean_text::reduce_to_single_whitespace
• clean_text::strip_unwanted_chars
• extract::extract_urls
• local_content::load_content_path
• splitting::rule_based::split_text_into_indices
• splitting::rule_based::split_text_into_sentences

Statics

• clean_text::CITATIONS_REGEX
• clean_text::END_OF_LINE_REGEX
• clean_text::END_OF_LINE_SEQUENCES
• clean_text::END_OF_PARAGRAPH_REGEX
• clean_text::END_OF_PARAGRAPH_SEQUENCES
• clean_text::SINGLE_NEWLINE_REGEX
• clean_text::SINGLE_SPACE_REGEX
• clean_text::TWO_PLUS_NEWLINE_REGEX
• clean_text::UNWANTED_CHARS_REGEX
• clean_text::WHITE_SPACE_REGEX
• clean_text::WHITE_SPACE_SEQUENCES
• splitting::SINGLE_NEWLINE_REGEX
• splitting::TWO_PLUS_NEWLINE_REGEX
• splitting::rule_based::HANDLE_FLOATS_WITHOUT_LEADING_ZERO
• splitting::rule_based::PAREN_REPAIR
• splitting::rule_based::QUOTE_REPAIR_REGEXES
• splitting::rule_based::QUOTE_TRANSFORMATIONS
• splitting::rule_based::REMOVE_ABBREVIATIONS
• splitting::rule_based::REMOVE_COMPOSITE_ABBREVIATIONS
• splitting::rule_based::REMOVE_FLOATING_POINT_NUMBERS
• splitting::rule_based::REMOVE_INITIALS
• splitting::rule_based::REMOVE_SENTENCE_ENDERS_BEFORE_PARENS
• splitting::rule_based::REMOVE_SUSPENSION_POINTS
• splitting::rule_based::UNSTICK_SENTENCES
• test_text::CHUNK_TESTS
• test_text::SPLIT_TESTS
• test_text::TEXT