1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
use crate::simple_match::*;

/// Methods to split a longer strong on a separator and return a vector of strings,
/// a tuple of two strings or single optional string segment
/// Note some methods may return empty segments in the case of leading, trailing or repeated separators
/// See notes below
pub trait ToSegments {

  /// Extract a vector of non-empty strings from a string-like object with a given separator
  /// excluding leading, trailing or double separators
  fn to_segments(&self, separator: &str) -> Vec<String>;

  /// Extract a vector of strings from a string-like object with a given separator
  fn to_parts(&self, separator: &str) -> Vec<String>;

  /// Extract only the head before the first occurrence of a separator
  fn to_head(&self, separator: &str) -> String;

  /// Extract only the first segment before the first occurrence of a non-initial separator
  fn to_first(&self, separator: &str) -> String;

  /// Extract only the remainder after the first occurrence of a non-initial separator
  fn to_remainder_end(&self, separator: &str) -> String;

  /// Extract only the last segment after the last occurrence of a non-final separator
  fn to_last(&self, separator: &str) -> String;

  /// Extract only the beginning before the last segment following the last occurrence of a non-final separator
  fn to_remainder_start(&self, separator: &str) -> String;

  /// Extract only the last segment
  fn to_end(&self, separator: &str) -> String;

  /// Extract a string-like segment identified by its index from the components of a string with a given separator
  /// e.g. String::from("10/11/2024") .to_segment(1) yields "11"
  fn to_segment(&self, separator: &str, index: i32) -> Option<String>;

  fn to_inner_segment(&self, groups: &[(&str, i32)]) -> Option<String>;

  /// extract the remainder after the head
  fn to_tail(&self, separator: &str) -> String;

  /// extract the first and last parts after the first occurrence of the separator
  fn to_head_tail(&self, separator: &str) -> (String, String);

  /// extract the first and last parts after the last occurrence of the separator
  fn to_start_end(&self, separator: &str) -> (String, String);

}

/// Implement string segment split and capture method for String
impl ToSegments for str {

  /// Splits a string on the exact separator, whether initial, final or repeated.
  /// May yield empty segments
  fn to_parts(&self, separator: &str) -> Vec<String> {
    let splitter = self.split(separator);
    splitter.into_iter().map(|s| s.to_string()).collect::<Vec<String>>()
  }

  /// Splits a string on a separator, but only returns an array of non-empty strings
  /// skipping leading, trailing or repeated separators that may otherwise yield empty strings
  fn to_segments(&self, separator: &str) -> Vec<String> {
    let splitter = self.split(separator);
    splitter.into_iter().map(|s| s.to_string()).filter(|s| s.len() > 0).collect::<Vec<String>>()
  }

  fn to_head(&self, separator: &str) -> String {
    if let Some((head, _tail)) = self.split_once(separator) {
      head.to_string()
    } else {
      self.to_owned()
    }
  }

  /// Extract only the last segment after the last occurrence of a non-final separator
  fn to_last(&self, separator: &str) -> String {
    let separator_len = separator.len();
    if self.ends_with(separator) && self.len() > separator_len {
      let end_index = self.len() - separator_len;
      self[0..end_index].to_string().to_end(separator)
    } else {
      self.to_end(separator)
    }
  }

  /// extract the last segment whether empty or not
  fn to_end(&self, separator: &str) -> String {
    let parts = self.to_parts(separator);
    if let Some(end) = parts.last() {
      end.to_owned()
    } else {
      self.to_owned()
    }
  }

  /// extract the remainder after the first split 
  /// or the whole string if the separator is absent
  fn to_tail(&self, separator: &str) -> String {
    let parts = self.to_parts(separator);
    let num_parts = parts.len();
    if num_parts > 0 {
      parts[1..num_parts].join(separator)
    } else {
      self.to_owned()
    }
  }

  /// Extract only the first segment before the first occurrence of a non-initial separator
  fn to_first(&self, separator: &str) -> String {
    let separator_len = separator.len();
    if self.starts_with(separator) && self.len() > separator_len {
      self[separator_len..self.len()].to_string().to_head(separator)
    } else {
      self.to_head(separator)
    }
  }

  /// Extract only the remainder after the first occurrence of a non-initial separator
  fn to_remainder_end(&self, separator: &str) -> String {
    let separator_len = separator.len();
    if self.starts_with(separator) && self.len() > separator_len {
      self[separator_len..].to_string().to_tail(separator)
    } else {
      self.to_tail(separator)
    }
  }
  
  /// Extract only the beginning before the last segment following the last occurrence of a non-final separator
  fn to_remainder_start(&self, separator: &str) -> String {
    let separator_len = separator.len();
    if self.ends_with(separator) && self.len() > separator_len {
      let end_index = self.len() - separator_len;
      self[0..end_index].to_string().to_tail(separator)
    } else {
      self.to_tail(separator)
    }
  }

  /// Extract an indexed segment yielded by splitting a string. 
  /// A negative index parameter will start from the end 
  fn to_segment(&self, separator: &str, index: i32) -> Option<String> {
    let parts = self.to_segments(separator);
    let num_parts = parts.len();
    let target_index = if index >= 0 { index as usize } else { (num_parts as i32 + index) as usize };
    if target_index < num_parts {
      if let Some(segment) = parts.get(target_index) {
        Some(segment.to_owned())
      } else {
        None
      }
    } else {
      None
    }
  }

  /// extract an inner segment via a set of tuples with separators and indices.
  /// e.g. [("/", 1), ("-", 2)] applied to "pictures/holiday-france-1983/originals" 
  /// would match "1983" as an optional string
  fn to_inner_segment(&self, groups: &[(&str, i32)]) -> Option<String> {
    if groups.len() > 0 {
      let mut matched: Option<String> = None;
      let mut current_string = self.to_string();
      for group in groups {
        if current_string.len() > 0 {
          let (separator, index) = group;
          matched = current_string.to_segment(*separator, *index);
          current_string = matched.clone().unwrap_or("".to_string());
        }
      }
      matched
    } else {
      None
    }
  }

  /// Extract a tuple of the head and remainder, like split_once but returns Strings
  fn to_head_tail(&self, separator: &str) -> (String, String) {
    if let Some((head, tail)) = self.split_once(separator) {
      (head.to_string(), tail.to_string())
    } else {
      ("".to_owned(), self.to_owned())
    }
  }

  /// Extract a tuple of the tail and remainder, like split_once in reverse and returning strings
  fn to_start_end(&self, separator: &str) -> (String, String) {
    let parts = self.to_parts(separator);
    let num_parts = parts.len();
    if num_parts > 1 {
      let end_index = num_parts - 1;
      let start = parts[0..end_index].join(separator);
      let end = self.to_end(separator);
      (start, end)
    } else {
      (self.to_owned(), "".to_string())
    }
  }

}


/// Methods to split a &str/String on the first matched separator character
pub trait ToSegmentsFromChars {
  
  /// Split a string into parts separated by any of the referenced split characters
  fn split_on_any_char(&self, separators: &[char]) -> Vec<String>;

  /// Split a string into a head and tail separated by the first instance of the first matching separator
  /// If none of the separators are matched, the first element is
  ///  an empty string and the second the whole string
  fn to_head_tail_on_any_char(&self, separators: &[char]) -> (String, String);

  /// Split a string into s start and tail separated by the last instance of the first matching separator
  /// If none of the separators are matched, the first element is
  ///  an empty string and the second the whole string
  fn to_start_end_on_any_char(&self, separators: &[char]) -> (String, String);
}

impl ToSegmentsFromChars for str {

  /// Split a string on any of the referenced characters
  fn split_on_any_char(&self, separators: &[char]) -> Vec<String> {
    let mut parts: Vec<String> = Vec::new();
    let mut has_match = false;
    let mut indices: Vec<usize> = Vec::new();
    for separator in separators {
      for matched_index in self.find_char_indices(*separator) {
        indices.push(matched_index);
      }
    }
    indices.sort_by(|a, b| a.cmp(b));
    let mut prev_start = 0;
    for index in indices {
      let segment = self[prev_start..index].to_string();
      parts.push(segment);
      has_match = true;
      prev_start = index + 1;
    }
    if has_match {
      parts.push(self[prev_start..].to_string());
      parts
    } else {
      vec![self.to_owned()]
    }
  }

  /// Split into head and tail components on the first occurrence of any of the referenced characters
  fn to_head_tail_on_any_char(&self, separators: &[char]) -> (String, String) {
    for ch in separators {
      if self.contains(*ch) {
        if let Some ((first, second)) = self.split_once(*ch) {
          return (first.to_string(), second.to_string());
        }
      }
    }
    ("".to_owned(), self.to_string())
  }

  /// Split into start and end components on the last occurrence of any of the referenced characters
  fn to_start_end_on_any_char(&self, separators: &[char]) -> (String, String) {
    for ch in separators {
      if self.contains(*ch) {
        if let Some ((first, second)) = self.rsplit_once(*ch) {
          return (first.to_string(), second.to_string());
        }
      }
    }
    (self.to_string(), "".to_owned())
  }

}