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
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
|
// Copyright 2014 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "components/secure_display/elide_url.h"
#include "base/logging.h"
#include "base/strings/string_split.h"
#include "base/strings/utf_string_conversions.h"
#include "net/base/escape.h"
#include "net/base/net_util.h"
#include "net/base/registry_controlled_domains/registry_controlled_domain.h"
#include "ui/gfx/text_elider.h"
#include "ui/gfx/text_utils.h"
#include "url/gurl.h"
#include "url/url_constants.h"
using base::UTF8ToUTF16;
using gfx::ElideText;
using gfx::GetStringWidthF;
using gfx::kEllipsisUTF16;
using gfx::kForwardSlash;
namespace {
#if !defined(OS_ANDROID)
const base::char16 kDot = '.';
// Build a path from the first |num_components| elements in |path_elements|.
// Prepends |path_prefix|, appends |filename|, inserts ellipsis if appropriate.
base::string16 BuildPathFromComponents(
const base::string16& path_prefix,
const std::vector<base::string16>& path_elements,
const base::string16& filename,
size_t num_components) {
// Add the initial elements of the path.
base::string16 path = path_prefix;
// Build path from first |num_components| elements.
for (size_t j = 0; j < num_components; ++j)
path += path_elements[j] + kForwardSlash;
// Add |filename|, ellipsis if necessary.
if (num_components != (path_elements.size() - 1))
path += base::string16(kEllipsisUTF16) + kForwardSlash;
path += filename;
return path;
}
// Takes a prefix (Domain, or Domain+subdomain) and a collection of path
// components and elides if possible. Returns a string containing the longest
// possible elided path, or an empty string if elision is not possible.
base::string16 ElideComponentizedPath(
const base::string16& url_path_prefix,
const std::vector<base::string16>& url_path_elements,
const base::string16& url_filename,
const base::string16& url_query,
const gfx::FontList& font_list,
float available_pixel_width) {
const size_t url_path_number_of_elements = url_path_elements.size();
CHECK(url_path_number_of_elements);
for (size_t i = url_path_number_of_elements - 1; i > 0; --i) {
base::string16 elided_path = BuildPathFromComponents(
url_path_prefix, url_path_elements, url_filename, i);
if (available_pixel_width >= GetStringWidthF(elided_path, font_list))
return ElideText(elided_path + url_query, font_list,
available_pixel_width, gfx::ELIDE_TAIL);
}
return base::string16();
}
// Splits the hostname in the |url| into sub-strings for the full hostname,
// the domain (TLD+1), and the subdomain (everything leading the domain).
void SplitHost(const GURL& url,
base::string16* url_host,
base::string16* url_domain,
base::string16* url_subdomain) {
// Get Host.
*url_host = UTF8ToUTF16(url.host());
// Get domain and registry information from the URL.
*url_domain =
UTF8ToUTF16(net::registry_controlled_domains::GetDomainAndRegistry(
url, net::registry_controlled_domains::EXCLUDE_PRIVATE_REGISTRIES));
if (url_domain->empty())
*url_domain = *url_host;
// Add port if required.
if (!url.port().empty()) {
*url_host += UTF8ToUTF16(":" + url.port());
*url_domain += UTF8ToUTF16(":" + url.port());
}
// Get sub domain.
const size_t domain_start_index = url_host->find(*url_domain);
base::string16 kWwwPrefix = UTF8ToUTF16("www.");
if (domain_start_index != base::string16::npos)
*url_subdomain = url_host->substr(0, domain_start_index);
if ((*url_subdomain == kWwwPrefix || url_subdomain->empty() ||
url.SchemeIsFile())) {
url_subdomain->clear();
}
}
#endif // !defined(OS_ANDROID)
} // namespace
namespace secure_display {
#if !defined(OS_ANDROID)
// TODO(pkasting): http://crbug.com/77883 This whole function gets
// kerning/ligatures/etc. issues potentially wrong by assuming that the width of
// a rendered string is always the sum of the widths of its substrings. Also I
// suspect it could be made simpler.
base::string16 ElideUrl(const GURL& url,
const gfx::FontList& font_list,
float available_pixel_width,
const std::string& languages) {
// Get a formatted string and corresponding parsing of the url.
url::Parsed parsed;
const base::string16 url_string =
net::FormatUrl(url, languages, net::kFormatUrlOmitAll,
net::UnescapeRule::SPACES, &parsed, NULL, NULL);
if (available_pixel_width <= 0)
return url_string;
// If non-standard, return plain eliding.
if (!url.IsStandard())
return ElideText(url_string, font_list, available_pixel_width,
gfx::ELIDE_TAIL);
// Now start eliding url_string to fit within available pixel width.
// Fist pass - check to see whether entire url_string fits.
const float pixel_width_url_string = GetStringWidthF(url_string, font_list);
if (available_pixel_width >= pixel_width_url_string)
return url_string;
// Get the path substring, including query and reference.
const size_t path_start_index = parsed.path.begin;
const size_t path_len = parsed.path.len;
base::string16 url_path_query_etc = url_string.substr(path_start_index);
base::string16 url_path = url_string.substr(path_start_index, path_len);
// Return general elided text if url minus the query fits.
const base::string16 url_minus_query =
url_string.substr(0, path_start_index + path_len);
if (available_pixel_width >= GetStringWidthF(url_minus_query, font_list))
return ElideText(url_string, font_list, available_pixel_width,
gfx::ELIDE_TAIL);
base::string16 url_host;
base::string16 url_domain;
base::string16 url_subdomain;
SplitHost(url, &url_host, &url_domain, &url_subdomain);
// If this is a file type, the path is now defined as everything after ":".
// For example, "C:/aa/aa/bb", the path is "/aa/bb/cc". Interesting, the
// domain is now C: - this is a nice hack for eliding to work pleasantly.
if (url.SchemeIsFile()) {
// Split the path string using ":"
const base::string16 kColon(1, ':');
std::vector<base::string16> file_path_split = base::SplitString(
url_path, kColon, base::TRIM_WHITESPACE, base::SPLIT_WANT_ALL);
if (file_path_split.size() > 1) { // File is of type "file:///C:/.."
url_host.clear();
url_domain.clear();
url_subdomain.clear();
url_host = url_domain = file_path_split.at(0).substr(1) + kColon;
url_path_query_etc = url_path = file_path_split.at(1);
}
}
// Second Pass - remove scheme - the rest fits.
const float pixel_width_url_host = GetStringWidthF(url_host, font_list);
const float pixel_width_url_path =
GetStringWidthF(url_path_query_etc, font_list);
if (available_pixel_width >= pixel_width_url_host + pixel_width_url_path)
return url_host + url_path_query_etc;
// Third Pass: Subdomain, domain and entire path fits.
const float pixel_width_url_domain = GetStringWidthF(url_domain, font_list);
const float pixel_width_url_subdomain =
GetStringWidthF(url_subdomain, font_list);
if (available_pixel_width >=
pixel_width_url_subdomain + pixel_width_url_domain + pixel_width_url_path)
return url_subdomain + url_domain + url_path_query_etc;
// Query element.
base::string16 url_query;
const float kPixelWidthDotsTrailer =
GetStringWidthF(base::string16(kEllipsisUTF16), font_list);
if (parsed.query.is_nonempty()) {
url_query = UTF8ToUTF16("?") + url_string.substr(parsed.query.begin);
if (available_pixel_width >=
(pixel_width_url_subdomain + pixel_width_url_domain +
pixel_width_url_path - GetStringWidthF(url_query, font_list))) {
return ElideText(url_subdomain + url_domain + url_path_query_etc,
font_list, available_pixel_width, gfx::ELIDE_TAIL);
}
}
// Parse url_path using '/'.
std::vector<base::string16> url_path_elements =
base::SplitString(url_path, base::string16(1, kForwardSlash),
base::TRIM_WHITESPACE, base::SPLIT_WANT_ALL);
// Get filename - note that for a path ending with /
// such as www.google.com/intl/ads/, the file name is ads/.
base::string16 url_filename(
url_path_elements.empty() ? base::string16() : url_path_elements.back());
size_t url_path_number_of_elements = url_path_elements.size();
if (url_filename.empty() && (url_path_number_of_elements > 1)) {
// Path ends with a '/'.
--url_path_number_of_elements;
url_filename =
url_path_elements[url_path_number_of_elements - 1] + kForwardSlash;
}
const size_t kMaxNumberOfUrlPathElementsAllowed = 1024;
if (url_path_number_of_elements <= 1 ||
url_path_number_of_elements > kMaxNumberOfUrlPathElementsAllowed) {
// No path to elide, or too long of a path (could overflow in loop below)
// Just elide this as a text string.
return ElideText(url_subdomain + url_domain + url_path_query_etc, font_list,
available_pixel_width, gfx::ELIDE_TAIL);
}
// Start eliding the path and replacing elements by ".../".
const base::string16 kEllipsisAndSlash =
base::string16(kEllipsisUTF16) + kForwardSlash;
const float pixel_width_ellipsis_slash =
GetStringWidthF(kEllipsisAndSlash, font_list);
// Check with both subdomain and domain.
base::string16 elided_path = ElideComponentizedPath(
url_subdomain + url_domain, url_path_elements, url_filename, url_query,
font_list, available_pixel_width);
if (!elided_path.empty())
return elided_path;
// Check with only domain.
// If a subdomain is present, add an ellipsis before domain.
// This is added only if the subdomain pixel width is larger than
// the pixel width of kEllipsis. Otherwise, subdomain remains,
// which means that this case has been resolved earlier.
base::string16 url_elided_domain = url_subdomain + url_domain;
if (pixel_width_url_subdomain > kPixelWidthDotsTrailer) {
if (!url_subdomain.empty())
url_elided_domain = kEllipsisAndSlash[0] + url_domain;
else
url_elided_domain = url_domain;
elided_path = ElideComponentizedPath(url_elided_domain, url_path_elements,
url_filename, url_query, font_list,
available_pixel_width);
if (!elided_path.empty())
return elided_path;
}
// Return elided domain/.../filename anyway.
base::string16 final_elided_url_string(url_elided_domain);
const float url_elided_domain_width =
GetStringWidthF(url_elided_domain, font_list);
// A hack to prevent trailing ".../...".
if ((available_pixel_width - url_elided_domain_width) >
pixel_width_ellipsis_slash + kPixelWidthDotsTrailer +
GetStringWidthF(base::ASCIIToUTF16("UV"), font_list)) {
final_elided_url_string += BuildPathFromComponents(
base::string16(), url_path_elements, url_filename, 1);
} else {
final_elided_url_string += url_path;
}
return ElideText(final_elided_url_string, font_list, available_pixel_width,
gfx::ELIDE_TAIL);
}
base::string16 ElideHost(const GURL& url,
const gfx::FontList& font_list,
float available_pixel_width) {
base::string16 url_host;
base::string16 url_domain;
base::string16 url_subdomain;
SplitHost(url, &url_host, &url_domain, &url_subdomain);
const float pixel_width_url_host = GetStringWidthF(url_host, font_list);
if (available_pixel_width >= pixel_width_url_host)
return url_host;
if (url_subdomain.empty())
return url_domain;
const float pixel_width_url_domain = GetStringWidthF(url_domain, font_list);
float subdomain_width = available_pixel_width - pixel_width_url_domain;
if (subdomain_width <= 0)
return base::string16(kEllipsisUTF16) + kDot + url_domain;
const base::string16 elided_subdomain =
ElideText(url_subdomain, font_list, subdomain_width, gfx::ELIDE_HEAD);
return elided_subdomain + url_domain;
}
#endif // !defined(OS_ANDROID)
base::string16 FormatUrlForSecurityDisplay(const GURL& url,
const std::string& languages) {
if (!url.is_valid() || url.is_empty() || !url.IsStandard())
return net::FormatUrl(url, languages);
const base::string16 colon(base::ASCIIToUTF16(":"));
const base::string16 scheme_separator(
base::ASCIIToUTF16(url::kStandardSchemeSeparator));
if (url.SchemeIsFile()) {
return base::ASCIIToUTF16(url::kFileScheme) + scheme_separator +
base::UTF8ToUTF16(url.path());
}
if (url.SchemeIsFileSystem()) {
const GURL* inner_url = url.inner_url();
if (inner_url->SchemeIsFile()) {
return base::ASCIIToUTF16(url::kFileSystemScheme) + colon +
FormatUrlForSecurityDisplay(*inner_url, languages) +
base::UTF8ToUTF16(url.path());
}
return base::ASCIIToUTF16(url::kFileSystemScheme) + colon +
FormatUrlForSecurityDisplay(*inner_url, languages);
}
const GURL origin = url.GetOrigin();
const std::string& scheme = origin.scheme();
const std::string& host = origin.host();
base::string16 result = base::UTF8ToUTF16(scheme);
result += scheme_separator;
result += base::UTF8ToUTF16(host);
const int port = origin.IntPort();
const int default_port = url::DefaultPortForScheme(
scheme.c_str(), static_cast<int>(scheme.length()));
if (port != url::PORT_UNSPECIFIED && port != default_port)
result += colon + base::UTF8ToUTF16(origin.port());
return result;
}
} // namespace secure_display
|