summaryrefslogtreecommitdiff
path: root/lisp/international/textsec.el
blob: d0d435ed7dc591f0e5b00fc7730f2d4d9e469712 (plain)
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
;;; textsec.el --- Functions for handling homoglyphs and the like  -*- lexical-binding: t; -*-

;; Copyright (C) 2022 Free Software Foundation, Inc.

;; This file is part of GNU Emacs.

;; GNU Emacs is free software: you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
;; the Free Software Foundation, either version 3 of the License, or
;; (at your option) any later version.

;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
;; GNU General Public License for more details.

;; You should have received a copy of the GNU General Public License
;; along with GNU Emacs.  If not, see <https://www.gnu.org/licenses/>.

;;; Commentary:

;;

;;; Code:

(require 'cl-lib)
(require 'uni-confusable)
(require 'ucs-normalize)
(require 'idna-mapping)
(require 'puny)

(defvar textsec--char-scripts nil)

(eval-and-compile
  (defun textsec--create-script-table (data)
    "Create the textsec--char-scripts char table."
    (setq textsec--char-scripts (make-char-table nil))
    (dolist (scripts data)
      (dolist (range (cadr scripts))
        (set-char-table-range textsec--char-scripts
                              range (car scripts)))))
  (require 'uni-scripts))

(defun textsec-scripts (string)
  "Return a list of Unicode scripts used in STRING.
The scripts returned by this function use the Unicode Script property
as defined by the Unicode Standard Annex 24 (UAX#24)."
  (seq-map (lambda (char)
             (elt textsec--char-scripts char))
           string))

(defun textsec-single-script-p (string)
  "Return non-nil if STRING is all in a single Unicode script.

Note that the concept of \"single script\" used by this function
isn't obvious -- some mixtures of scripts count as a \"single
script\".  See

  https://www.unicode.org/reports/tr39/#Mixed_Script_Detection

for details.  The Unicode scripts are as defined by the
Unicode Standard Annex 24 (UAX#24)."
  (let ((scripts (mapcar
                  (lambda (s)
                    (append s
                            ;; Some scripts used in East Asia are
                            ;; commonly used across borders, so we add
                            ;; those.
                            (mapcan (lambda (script)
                                      (copy-sequence
                                       (textsec--augment-script script)))
                                    s)))
                         (textsec-scripts string))))
    (catch 'empty
      (cl-loop for s1 in scripts
               do (cl-loop for s2 in scripts
                           ;; Common/inherited chars can be used in
                           ;; text with all scripts.
                           when (and (not (memq 'common s1))
                                     (not (memq 'common s2))
                                     (not (memq 'inherited s1))
                                     (not (memq 'inherited s2))
                                     (not (seq-intersection s1 s2)))
                           do (throw 'empty nil)))
      t)))

(defun textsec--augment-script (script)
  (cond
   ((eq script 'han)
    '(hangul japan korea))
   ((or (eq script 'hiragana)
        (eq script 'katakana))
    '(japan))
   ((or (eq script 'hangul)
        (eq script 'bopomofo))
    '(korea))))

(defun textsec-covering-scripts (string)
  "Return a minimal list of scripts used in STRING.
Note that a string may have several different minimal cover sets.
The scripts are as defined by the Unicode Standard Annex 24 (UAX#24)."
  (let* ((scripts (textsec-scripts string))
         (set (car scripts)))
    (dolist (s scripts)
      (setq set (seq-union set (seq-difference s set))))
    (sort (delq 'common (delq 'inherited set)) #'string<)))

(defun textsec-restriction-level (string)
  "Say what restriction level STRING qualifies for.
Levels are (in decreasing order of restrictiveness) `ascii-only',
`single-script', `highly-restrictive', `moderately-restrictive',
`minimally-restrictive' and `unrestricted'."
  (let ((scripts (textsec-covering-scripts string)))
  (cond
   ((string-match "\\`[[:ascii:]]+\\'" string)
    'ascii-only)
   ((textsec-single-script-p string)
    'single-script)
   ((or (null (seq-difference scripts '(latin han hiragana katakana)))
        (null (seq-difference scripts '(latin han bopomofo)))
        (null (seq-difference scripts '(latin han hangul))))
    'highly-restrictive)
   ((and (= (length scripts) 2)
         (memq 'latin scripts)
         ;; This list comes from
         ;; https://www.unicode.org/reports/tr31/#Table_Recommended_Scripts
         ;; (but is without latin, cyrillic and greek).
         (seq-intersection scripts
                           '(arabic
                             armenian
                             bengali
                             bopomofo
                             devanagari
                             ethiopic
                             georgian
                             gujarati
                             gurmukhi
                             hangul
                             han
                             hebrew
                             hiragana
                             katakana
                             kannada
                             khmer
                             lao
                             malayalam
                             myanmar
                             oriya
                             sinhala
                             tamil
                             telugu
                             thaana
                             thai
                             tibetan)))
    ;; The string is covered by Latin and any one other Recommended
    ;; script, except Cyrillic, Greek.
    'moderately-retrictive)
   ;; Fixme `minimally-restrictive' -- needs well-formedness criteria
   ;; and Identifier Profile.
   (t
    'unrestricted))))

(defun textsec-mixed-numbers-p (string)
  "Return non-nil if there are numbers from different decimal systems in STRING."
  (>
   (length
    (seq-uniq
     (mapcar
      (lambda (char)
        (get-char-code-property char 'numeric-value))
      (seq-filter (lambda (char)
                    ;; We're selecting the characters that
                    ;; have a numeric property.
                    (eq (get-char-code-property char 'general-category)
                        'Nd))
                  string))))
   1))

(defun textsec-ascii-confusable-p (string)
  "Return non-nil if STRING isn't ASCII, but is confusable with ASCII."
  (and (not (eq (textsec-restriction-level string) 'ascii-only))
       (eq (textsec-restriction-level (textsec-unconfuse-string string))
           'ascii-only)))

(defun textsec-unconfuse-string (string)
  "Return a de-confused version of STRING.
This algorithm is described in:

  https://www.unicode.org/reports/tr39/#Confusable_Detection"
  (ucs-normalize-NFD-string
   (apply #'concat
          (seq-map (lambda (char)
                     (or (gethash char uni-confusable-table)
                         (string char)))
                   (ucs-normalize-NFD-string string)))))

(defun textsec-resolved-script-set (string)
  "Return the resolved script set for STRING.
This is the minimal covering script set for STRING, but is nil is
STRING isn't a single script string."
  (and (textsec-single-script-p string)
       (textsec-covering-scripts string)))

(defun textsec-single-script-confusable-p (string1 string2)
  "Say whether STRING1 and STRING2 are single script confusables."
  (and (equal (textsec-unconfuse-string string1)
              (textsec-unconfuse-string string2))
       ;; And they have to have at least one resolved script in
       ;; common.
       (seq-intersection (textsec-resolved-script-set string1)
                         (textsec-resolved-script-set string2))))

(defun textsec-mixed-script-confusable-p (string1 string2)
  "Say whether STRING1 and STRING2 are mixed script confusables."
  (and (equal (textsec-unconfuse-string string1)
              (textsec-unconfuse-string string2))
       ;; And they have no resolved scripts in common.
       (null (seq-intersection (textsec-resolved-script-set string1)
                               (textsec-resolved-script-set string2)))))

(defun textsec-whole-script-confusable-p (string1 string2)
  "Say whether STRING1 and STRING2 are whole script confusables."
  (and (textsec-mixed-script-confusable-p string1 string2)
       (textsec-single-script-p string1)
       (textsec-single-script-p string2)))

(defun textsec-domain-suspicious-p (domain)
  (catch 'found
    (seq-do
     (lambda (char)
       (when (eq (elt idna-mapping-table char) t)
         (throw 'found (format "Disallowed character: `%s' (#x%x)"
                               (string char) char))))
     domain)
    (unless (puny-highly-restrictive-domain-p domain)
      (throw 'found "%s is not highly restrictive"))
    nil))

(provide 'textsec)

;;; textsec.el ends here