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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
|
// Scintilla source code edit control
/** @file WordList.cxx
** Hold a list of words.
**/
// Copyright 1998-2002 by Neil Hodgson <neilh@scintilla.org>
// The License.txt file describes the conditions under which this software may be distributed.
#include <cstdlib>
#include <cassert>
#include <cstring>
#include <string>
#include <algorithm>
#include <iterator>
#include <memory>
#include "WordList.h"
using namespace Lexilla;
namespace {
/**
* Creates an array that points into each word in the string and puts \0 terminators
* after each word.
*/
std::unique_ptr<char *[]> ArrayFromWordList(char *wordlist, size_t slen, size_t *len, bool onlyLineEnds = false) {
assert(wordlist);
size_t words = 0;
// For rapid determination of whether a character is a separator, build
// a look up table.
bool wordSeparator[256] = {}; // Initialise all to false.
wordSeparator[static_cast<unsigned int>('\r')] = true;
wordSeparator[static_cast<unsigned int>('\n')] = true;
if (!onlyLineEnds) {
wordSeparator[static_cast<unsigned int>(' ')] = true;
wordSeparator[static_cast<unsigned int>('\t')] = true;
}
unsigned char prev = '\n';
for (int j = 0; wordlist[j]; j++) {
const unsigned char curr = wordlist[j];
if (!wordSeparator[curr] && wordSeparator[prev])
words++;
prev = curr;
}
std::unique_ptr<char *[]> keywords = std::make_unique<char *[]>(words + 1);
size_t wordsStore = 0;
if (words) {
unsigned char previous = '\0';
for (size_t k = 0; k < slen; k++) {
if (!wordSeparator[static_cast<unsigned char>(wordlist[k])]) {
if (!previous) {
keywords[wordsStore] = &wordlist[k];
wordsStore++;
}
} else {
wordlist[k] = '\0';
}
previous = wordlist[k];
}
}
assert(wordsStore < (words + 1));
keywords[wordsStore] = &wordlist[slen];
*len = wordsStore;
return keywords;
}
bool cmpWords(const char *a, const char *b) noexcept {
return strcmp(a, b) < 0;
}
}
WordList::WordList(bool onlyLineEnds_) noexcept :
words(nullptr), list(nullptr), len(0), onlyLineEnds(onlyLineEnds_) {
// Prevent warnings by static analyzers about uninitialized starts.
starts[0] = -1;
}
WordList::~WordList() {
Clear();
}
WordList::operator bool() const noexcept {
return len != 0;
}
bool WordList::operator!=(const WordList &other) const noexcept {
if (len != other.len)
return true;
for (size_t i=0; i<len; i++) {
if (strcmp(words[i], other.words[i]) != 0)
return true;
}
return false;
}
int WordList::Length() const noexcept {
return static_cast<int>(len);
}
void WordList::Clear() noexcept {
delete []list;
list = nullptr;
delete []words;
words = nullptr;
len = 0;
}
bool WordList::Set(const char *s) {
const size_t lenS = strlen(s) + 1;
std::unique_ptr<char[]> listTemp = std::make_unique<char[]>(lenS);
memcpy(listTemp.get(), s, lenS);
size_t lenTemp = 0;
std::unique_ptr<char *[]> wordsTemp = ArrayFromWordList(listTemp.get(), lenS - 1, &lenTemp, onlyLineEnds);
std::sort(wordsTemp.get(), wordsTemp.get() + lenTemp, cmpWords);
if (lenTemp == len) {
bool changed = false;
for (size_t i = 0; i < lenTemp; i++) {
if (strcmp(words[i], wordsTemp[i]) != 0) {
changed = true;
break;
}
}
if (!changed) {
return false;
}
}
Clear();
words = wordsTemp.release();
list = listTemp.release();
len = lenTemp;
std::fill(starts, std::end(starts), -1);
for (int l = static_cast<int>(len - 1); l >= 0; l--) {
unsigned char const indexChar = words[l][0];
starts[indexChar] = l;
}
return true;
}
/** Check whether a string is in the list.
* List elements are either exact matches or prefixes.
* Prefix elements start with '^' and match all strings that start with the rest of the element
* so '^GTK_' matches 'GTK_X', 'GTK_MAJOR_VERSION', and 'GTK_'.
*/
bool WordList::InList(const char *s) const noexcept {
if (!words)
return false;
const char first = s[0];
const unsigned char firstChar = first;
int j = starts[firstChar];
if (j >= 0) {
while (words[j][0] == first) {
if (s[1] == words[j][1]) {
const char *a = words[j] + 1;
const char *b = s + 1;
while (*a && *a == *b) {
a++;
b++;
}
if (!*a && !*b)
return true;
}
j++;
}
}
j = starts[static_cast<unsigned int>('^')];
if (j >= 0) {
while (words[j][0] == '^') {
const char *a = words[j] + 1;
const char *b = s;
while (*a && *a == *b) {
a++;
b++;
}
if (!*a)
return true;
j++;
}
}
return false;
}
/** convenience overload so can easily call with std::string.
*/
bool WordList::InList(const std::string &s) const noexcept {
return InList(s.c_str());
}
/** similar to InList, but word s can be a substring of keyword.
* eg. the keyword define is defined as def~ine. This means the word must start
* with def to be a keyword, but also defi, defin and define are valid.
* The marker is ~ in this case.
*/
bool WordList::InListAbbreviated(const char *s, const char marker) const noexcept {
if (!words)
return false;
const char first = s[0];
const unsigned char firstChar = first;
int j = starts[firstChar];
if (j >= 0) {
while (words[j][0] == first) {
bool isSubword = false;
int start = 1;
if (words[j][1] == marker) {
isSubword = true;
start++;
}
if (s[1] == words[j][start]) {
const char *a = words[j] + start;
const char *b = s + 1;
while (*a && *a == *b) {
a++;
if (*a == marker) {
isSubword = true;
a++;
}
b++;
}
if ((!*a || isSubword) && !*b)
return true;
}
j++;
}
}
j = starts[static_cast<unsigned int>('^')];
if (j >= 0) {
while (words[j][0] == '^') {
const char *a = words[j] + 1;
const char *b = s;
while (*a && *a == *b) {
a++;
b++;
}
if (!*a)
return true;
j++;
}
}
return false;
}
/** similar to InListAbbreviated, but word s can be an abridged version of a keyword.
* eg. the keyword is defined as "after.~:". This means the word must have a prefix (begins with) of
* "after." and suffix (ends with) of ":" to be a keyword, Hence "after.field:" , "after.form.item:" are valid.
* Similarly "~.is.valid" keyword is suffix only... hence "field.is.valid" , "form.is.valid" are valid.
* The marker is ~ in this case.
* No multiple markers check is done and wont work.
*/
bool WordList::InListAbridged(const char *s, const char marker) const noexcept {
if (!words)
return false;
const char first = s[0];
const unsigned char firstChar = first;
int j = starts[firstChar];
if (j >= 0) {
while (words[j][0] == first) {
const char *a = words[j];
const char *b = s;
while (*a && *a == *b) {
a++;
if (*a == marker) {
a++;
const size_t suffixLengthA = strlen(a);
const size_t suffixLengthB = strlen(b);
if (suffixLengthA >= suffixLengthB)
break;
b = b + suffixLengthB - suffixLengthA - 1;
}
b++;
}
if (!*a && !*b)
return true;
j++;
}
}
j = starts[static_cast<unsigned int>(marker)];
if (j >= 0) {
while (words[j][0] == marker) {
const char *a = words[j] + 1;
const char *b = s;
const size_t suffixLengthA = strlen(a);
const size_t suffixLengthB = strlen(b);
if (suffixLengthA > suffixLengthB) {
j++;
continue;
}
b = b + suffixLengthB - suffixLengthA;
while (*a && *a == *b) {
a++;
b++;
}
if (!*a && !*b)
return true;
j++;
}
}
return false;
}
const char *WordList::WordAt(int n) const noexcept {
return words[n];
}
|