rumtk_core/
search.rs

1/*
2 * rumtk attempts to implement HL7 and medical protocols for interoperability in medicine.
3 * This toolkit aims to be reliable, simple, performant, and standards compliant.
4 * Copyright (C) 2024  Luis M. Santos, M.D.
5 * Copyright (C) 2025  MedicalMasses L.L.C.
6 *
7 * This library is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
11 *
12 * This library is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
15 * Lesser General Public License for more details.
16 *
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with this library; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
20 */
21
22pub mod rumtk_search {
23    use crate::cache::{get_or_set_from_cache, new_cache, AHashMap, LazyRUMCache};
24    use crate::rumtk_cache_fetch;
25    use crate::strings::{CompactStringExt, RUMString};
26    use regex::Regex;
27    /**************************** Globals **************************************/
28    static mut re_cache: RegexCache = new_cache();
29    /**************************** Constants**************************************/
30    const DEFAULT_REGEX_CACHE_PAGE_SIZE: usize = 10;
31    /**************************** Types *****************************************/
32    pub type RegexCache = LazyRUMCache<RUMString, Regex>;
33    pub type SearchGroups = AHashMap<RUMString, RUMString>;
34    pub type CapturedList = Vec<RUMString>;
35
36    /**************************** Traits ****************************************/
37
38    /**************************** Helpers ***************************************/
39    fn compile_regex(expr: &RUMString) -> Regex {
40        Regex::new(expr).unwrap()
41    }
42
43    ///
44    /// Finds all of the named regex captures and generates a hash table with the results assorted
45    /// into key-value pairs. The keys are the names found in the regex expression. The value is
46    /// the match corresponding to the named capture.
47    ///
48    /// This function returns an instance of SearchGroup which is the hash map.
49    ///
50    pub fn string_search_named_captures(input: &str, expr: &str, default: &str) -> SearchGroups {
51        let re = rumtk_cache_fetch!(&mut re_cache, &RUMString::from(expr), compile_regex);
52        let names: Vec<&str> = re
53            .capture_names()
54            .skip(1)
55            .map(|x| x.unwrap_or(""))
56            .collect();
57        let mut clean_names: Vec<&str> = Vec::with_capacity(names.len());
58        let mut groups = SearchGroups::with_capacity(DEFAULT_REGEX_CACHE_PAGE_SIZE);
59
60        for name in &names {
61            if !name.is_empty() {
62                clean_names.push(name);
63            }
64        }
65
66        if clean_names.is_empty() {
67            return groups;
68        }
69
70        for name in &clean_names {
71            groups.insert(RUMString::from(name.to_string()), RUMString::from(default));
72        }
73
74        for cap in re.captures_iter(input).map(|c| c) {
75            for name in &clean_names {
76                let val = cap.name(name).map_or("", |s| s.as_str());
77                if !val.is_empty() {
78                    groups.insert(RUMString::from(name.to_string()), RUMString::from(val));
79                }
80            }
81        }
82
83        groups
84    }
85
86    ///
87    /// Finds all of the regex captures regardless of name status and compile them into a list
88    /// of strings. Elsewhere, this provides a simple way to iterate through the contents that
89    /// were inside a group \(\).
90    ///
91    /// This function returns an instance of CapturedList which is the list of strings.
92    ///
93    pub fn string_search_all_captures(input: &str, expr: &str, default: &str) -> CapturedList {
94        let re = rumtk_cache_fetch!(&mut re_cache, &RUMString::from(expr), compile_regex);
95        let mut capture_list = CapturedList::with_capacity(DEFAULT_REGEX_CACHE_PAGE_SIZE);
96
97        for caps in re.captures_iter(input) {
98            for c in caps.iter().skip(1) {
99                let c_str = c.unwrap().as_str();
100                capture_list.push(RUMString::from(c_str));
101            }
102        }
103
104        capture_list
105    }
106
107    ///
108    /// Given a string input and a compiled RegEx, look for all matches and put them in a string
109    /// list for easy iteration/access.
110    ///
111    pub fn string_list(input: &str, re: &Regex) -> CapturedList {
112        let mut list: Vec<RUMString> = Vec::with_capacity(DEFAULT_REGEX_CACHE_PAGE_SIZE);
113        for itm in re.find_iter(input) {
114            list.push(RUMString::from(itm.as_str()));
115        }
116        list
117    }
118
119    ///
120    /// Given a string input and a RegEx string,
121    /// ```text
122    ///     - Compile the regex if not done so already.
123    ///     - Do a string search for all regex matches.
124    ///     - Collapse/join the matches into a single output string using join_pattern as the join fragment.
125    /// ```
126    /// Use \" \" in join_pattern if you wish to have spaces in between matches.
127    ///
128    pub fn string_search(input: &str, expr: &str, join_pattern: &str) -> RUMString {
129        let re = rumtk_cache_fetch!(&mut re_cache, &RUMString::from(expr), compile_regex);
130        string_list(input, &re).join_compact(join_pattern)
131    }
132}
rumtk_core/search.rs

rumtk_core/
search.rs
