diff options
author | Robin Krahl <robin.krahl@ireas.org> | 2020-01-07 11:18:04 +0000 |
---|---|---|
committer | Daniel Mueller <deso@posteo.net> | 2020-01-08 09:20:25 -0800 |
commit | 5e20a29b4fdc8a2d442d1093681b396dcb4b816b (patch) | |
tree | 55ab083fa8999d2ccbb5e921c1ffe52560dca152 /heck/src/lib.rs | |
parent | 203e691f46d591a2cc8acdfd850fa9f5b0fb8a98 (diff) | |
download | nitrocli-5e20a29b4fdc8a2d442d1093681b396dcb4b816b.tar.gz nitrocli-5e20a29b4fdc8a2d442d1093681b396dcb4b816b.tar.bz2 |
Add structopt dependency in version 0.3.7
This patch series replaces argparse with structopt in the argument
handling code. As a first step, we need structopt as a dependency.
Import subrepo structopt/:structopt at efbdda4753592e27bc430fb01f7b9650b2f3174d
Import subrepo bitflags/:bitflags at 30668016aca6bd3b02c766e8347e0b4080d4c296
Import subrepo clap/:clap at 784524f7eb193e35f81082cc69454c8c21b948f7
Import subrepo heck/:heck at 093d56fbf001e1506e56dbfa38631d99b1066df1
Import subrepo proc-macro-error/:proc-macro-error at 6c4cfe79a622c5de8ae68557993542be46eacae2
Import subrepo proc-macro2/:proc-macro2 at d5d48eddca4566e5438e8a2cbed4a74e049544de
Import subrepo quote/:quote at 727436c6c137b20f0f34dde5d8fda2679b9747ad
Import subrepo rustversion/:rustversion at 0c5663313516263059ce9059ef81fc7a1cf655ca
Import subrepo syn-mid/:syn-mid at 5d3d85414a9e6674e1857ec22a87b96e04a6851a
Import subrepo syn/:syn at e87c27e87f6f4ef8919d0372bdb056d53ef0d8f3
Import subrepo textwrap/:textwrap at abcd618beae3f74841032aa5b53c1086b0a57ca2
Import subrepo unicode-segmentation/:unicode-segmentation at 637c9874c4fe0c205ff27787faf150a40295c6c3
Import subrepo unicode-width/:unicode-width at 3033826f8bf05e82724140a981d5941e48fce393
Import subrepo unicode-xid/:unicode-xid at 4baae9fffb156ba229665b972a9cd5991787ceb7
Diffstat (limited to 'heck/src/lib.rs')
-rw-r--r-- | heck/src/lib.rs | 165 |
1 files changed, 165 insertions, 0 deletions
diff --git a/heck/src/lib.rs b/heck/src/lib.rs new file mode 100644 index 0000000..c35ba34 --- /dev/null +++ b/heck/src/lib.rs @@ -0,0 +1,165 @@ +//! **heck** is a case conversion library. +//! +//! This library exists to provide case conversion between common cases like +//! CamelCase and snake_case. It is intended to be unicode aware, internally, +//! consistent, and reasonably well performing. +//! +//! ## Definition of a word boundary +//! +//! Word boundaries are defined as the "unicode words" defined in the +//! `unicode_segmentation` library, as well as within those words in this manner: +//! +//! 1. All underscore characters are considered word boundaries. +//! 2. If an uppercase character is followed by lowercase letters, a word boundary +//! is considered to be just prior to that uppercase character. +//! 3. If multiple uppercase characters are consecutive, they are considered to be +//! within a single word, except that the last will be part of the next word if it +//! is followed by lowercase characters (see rule 2). +//! +//! That is, "HelloWorld" is segmented `Hello|World` whereas "XMLHttpRequest" is +//! segmented `XML|Http|Request`. +//! +//! Characters not within words (such as spaces, punctuations, and underscores) +//! are not included in the output string except as they are a part of the case +//! being converted to. Multiple adjacent word boundaries (such as a series of +//! underscores) are folded into one. ("hello__world" in snake case is therefore +//! "hello_world", not the exact same string). Leading or trailing word boundary +//! indicators are dropped, except insofar as CamelCase capitalizes the first word. +//! +//! ### Cases contained in this library: +//! +//! 1. CamelCase +//! 2. snake_case +//! 3. kebab-case +//! 4. SHOUTY_SNAKE_CASE +//! 5. mixedCase +//! 6. Title Case +#![deny(missing_docs)] +extern crate unicode_segmentation; + +mod camel; +mod kebab; +mod mixed; +mod shouty_snake; +mod snake; +mod title; + +pub use camel::CamelCase; +pub use kebab::KebabCase; +pub use mixed::MixedCase; +pub use shouty_snake::{ShoutySnakeCase, ShoutySnekCase}; +pub use snake::{SnakeCase, SnekCase}; +pub use title::TitleCase; + +use unicode_segmentation::UnicodeSegmentation; + +fn transform<F, G>(s: &str, with_word: F, boundary: G) -> String +where + F: Fn(&str, &mut String), + G: Fn(&mut String) +{ + + /// Tracks the current 'mode' of the transformation algorithm as it scans the input string. + /// + /// The mode is a tri-state which tracks the case of the last cased character of the current + /// word. If there is no cased character (either lowercase or uppercase) since the previous + /// word boundary, than the mode is `Boundary`. If the last cased character is lowercase, then + /// the mode is `Lowercase`. Othertherwise, the mode is `Uppercase`. + #[derive(Clone, Copy, PartialEq)] + enum WordMode { + /// There have been no lowercase or uppercase characters in the current word. + Boundary, + /// The previous cased character in the current word is lowercase. + Lowercase, + /// The previous cased character in the current word is uppercase. + Uppercase, + } + + let mut out = String::new(); + let mut first_word = true; + + for word in s.unicode_words() { + let mut char_indices = word.char_indices().peekable(); + let mut init = 0; + let mut mode = WordMode::Boundary; + + while let Some((i, c)) = char_indices.next() { + // Skip underscore characters + if c == '_' { + if init == i { init += 1; } + continue + } + + if let Some(&(next_i, next)) = char_indices.peek() { + + // The mode including the current character, assuming the current character does + // not result in a word boundary. + let next_mode = if c.is_lowercase() { + WordMode::Lowercase + } else if c.is_uppercase() { + WordMode::Uppercase + } else { + mode + }; + + // Word boundary after if next is underscore or current is + // not uppercase and next is uppercase + if next == '_' || (next_mode == WordMode::Lowercase && next.is_uppercase()) { + if !first_word { boundary(&mut out); } + with_word(&word[init..next_i], &mut out); + first_word = false; + init = next_i; + mode = WordMode::Boundary; + + // Otherwise if current and previous are uppercase and next + // is lowercase, word boundary before + } else if mode == WordMode::Uppercase && c.is_uppercase() && next.is_lowercase() { + if !first_word { boundary(&mut out); } + else { first_word = false; } + with_word(&word[init..i], &mut out); + init = i; + mode = WordMode::Boundary; + + // Otherwise no word boundary, just update the mode + } else { + mode = next_mode; + } + } else { + // Collect trailing characters as a word + if !first_word { boundary(&mut out); } + else { first_word = false; } + with_word(&word[init..], &mut out); + break; + } + } + } + + out +} + +fn lowercase(s: &str, out: &mut String) { + let mut chars = s.chars().peekable(); + while let Some(c) = chars.next() { + if c == 'Σ' && chars.peek().is_none() { + out.push('ς'); + } else { + out.extend(c.to_lowercase()); + } + } +} + +fn uppercase(s: &str, out: &mut String ) { + for c in s.chars() { + out.extend(c.to_uppercase()) + } +} + +fn capitalize(s: &str, out: &mut String) { + let mut char_indices = s.char_indices(); + if let Some((_, c)) = char_indices.next() { + out.extend(c.to_uppercase()); + if let Some((i, _)) = char_indices.next() { + lowercase(&s[i..], out); + } + } +} |