summaryrefslogtreecommitdiffstats
path: root/intl/uconv/nsTextToSubURI.cpp
blob: 4ace970357f9ae006a424fb2133d02730cfd413b (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
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
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
#include "nsString.h"
#include "nsIUnicodeEncoder.h"
#include "nsIUnicodeDecoder.h"
#include "nsITextToSubURI.h"
#include "nsEscape.h"
#include "nsTextToSubURI.h"
#include "nsCRT.h"
#include "mozilla/dom/EncodingUtils.h"
#include "mozilla/Preferences.h"
#include "nsISupportsPrimitives.h"

using mozilla::dom::EncodingUtils;

// Fallback value for the pref "network.IDN.blacklist_chars".
// UnEscapeURIForUI allows unescaped space; other than that, this is
// the same as the default "network.IDN.blacklist_chars" value.
static const char16_t sNetworkIDNBlacklistChars[] =
{
/*0x0020,*/
          0x00A0, 0x00BC, 0x00BD, 0x00BE, 0x01C3, 0x02D0, 0x0337,
  0x0338, 0x0589, 0x058A, 0x05C3, 0x05F4, 0x0609, 0x060A, 0x066A, 0x06D4,
  0x0701, 0x0702, 0x0703, 0x0704, 0x115F, 0x1160, 0x1735, 0x2000,
  0x2001, 0x2002, 0x2003, 0x2004, 0x2005, 0x2006, 0x2007, 0x2008,
  0x2009, 0x200A, 0x200B, 0x200E, 0x200F, 0x2010, 0x2019, 0x2024, 0x2027, 0x2028,
  0x2029, 0x202A, 0x202B, 0x202C, 0x202D, 0x202E, 0x202F, 0x2039,
  0x203A, 0x2041, 0x2044, 0x2052, 0x205F, 0x2153, 0x2154, 0x2155,
  0x2156, 0x2157, 0x2158, 0x2159, 0x215A, 0x215B, 0x215C, 0x215D,
  0x215E, 0x215F, 0x2215, 0x2236, 0x23AE, 0x2571, 0x29F6, 0x29F8,
  0x2AFB, 0x2AFD, 0x2FF0, 0x2FF1, 0x2FF2, 0x2FF3, 0x2FF4, 0x2FF5,
  0x2FF6, 0x2FF7, 0x2FF8, 0x2FF9, 0x2FFA, 0x2FFB, /*0x3000,*/ 0x3002,
  0x3014, 0x3015, 0x3033, 0x30A0, 0x3164, 0x321D, 0x321E, 0x33AE, 0x33AF,
  0x33C6, 0x33DF, 0xA789, 0xFE14, 0xFE15, 0xFE3F, 0xFE5D, 0xFE5E,
  0xFEFF, 0xFF0E, 0xFF0F, 0xFF61, 0xFFA0, 0xFFF9, 0xFFFA, 0xFFFB,
  0xFFFC, 0xFFFD
};

nsTextToSubURI::~nsTextToSubURI()
{
}

NS_IMPL_ISUPPORTS(nsTextToSubURI, nsITextToSubURI)

NS_IMETHODIMP  nsTextToSubURI::ConvertAndEscape(
  const char *charset, const char16_t *text, char **_retval) 
{
  if (!_retval) {
    return NS_ERROR_NULL_POINTER;
  }
  *_retval = nullptr;
  nsresult rv = NS_OK;
  
  if (!charset) {
    return NS_ERROR_NULL_POINTER;
  }

  nsDependentCString label(charset);
  nsAutoCString encoding;
  if (!EncodingUtils::FindEncodingForLabelNoReplacement(label, encoding)) {
    return NS_ERROR_UCONV_NOCONV;
  }
  nsCOMPtr<nsIUnicodeEncoder> encoder =
    EncodingUtils::EncoderForEncoding(encoding);
  rv = encoder->SetOutputErrorBehavior(nsIUnicodeEncoder::kOnError_Replace, nullptr, (char16_t)'?');
  if (NS_SUCCEEDED(rv) ) {
    char buf[256];
    char *pBuf = buf;
    int32_t ulen = text ? NS_strlen(text) : 0;
    int32_t outlen = 0;
    if (NS_SUCCEEDED(rv = encoder->GetMaxLength(text, ulen, &outlen))) {
      if (outlen >= 256) {
        pBuf = (char*)moz_xmalloc(outlen+1);
      }
      if (nullptr == pBuf) {
        outlen = 255;
        pBuf = buf;
      }
      int32_t bufLen = outlen;
      if (NS_SUCCEEDED(rv = encoder->Convert(text,&ulen, pBuf, &outlen))) {
        // put termination characters (e.g. ESC(B of ISO-2022-JP) if necessary
        int32_t finLen = bufLen - outlen;
        if (finLen > 0) {
          if (NS_SUCCEEDED(encoder->Finish((char *)(pBuf+outlen), &finLen))) {
            outlen += finLen;
          }
        }
        *_retval = nsEscape(pBuf, outlen, nullptr, url_XPAlphas);
        if (nullptr == *_retval) {
          rv = NS_ERROR_OUT_OF_MEMORY;
        }
      }
    }
    if (pBuf != buf) {
      free(pBuf);
    }
  }
  
  return rv;
}

NS_IMETHODIMP  nsTextToSubURI::UnEscapeAndConvert(
  const char *charset, const char *text, char16_t **_retval) 
{
  if(nullptr == _retval)
    return NS_ERROR_NULL_POINTER;
  if(nullptr == text) {
    // set empty string instead of returning error
    // due to compatibility for old version
    text = "";
  }
  *_retval = nullptr;
  nsresult rv = NS_OK;
  
  if (!charset) {
    return NS_ERROR_NULL_POINTER;
  }


  // unescape the string, unescape changes the input
  char *unescaped = NS_strdup(text);
  if (nullptr == unescaped)
    return NS_ERROR_OUT_OF_MEMORY;
  unescaped = nsUnescape(unescaped);
  NS_ASSERTION(unescaped, "nsUnescape returned null");

  nsDependentCString label(charset);
  nsAutoCString encoding;
  if (!EncodingUtils::FindEncodingForLabelNoReplacement(label, encoding)) {
    return NS_ERROR_UCONV_NOCONV;
  }
  nsCOMPtr<nsIUnicodeDecoder> decoder =
    EncodingUtils::DecoderForEncoding(encoding);
  char16_t *pBuf = nullptr;
  int32_t len = strlen(unescaped);
  int32_t outlen = 0;
  if (NS_SUCCEEDED(rv = decoder->GetMaxLength(unescaped, len, &outlen))) {
    pBuf = (char16_t *) moz_xmalloc((outlen+1)*sizeof(char16_t));
    if (nullptr == pBuf) {
      rv = NS_ERROR_OUT_OF_MEMORY;
    } else {
      if (NS_SUCCEEDED(rv = decoder->Convert(unescaped, &len, pBuf, &outlen))) {
        pBuf[outlen] = 0;
        *_retval = pBuf;
      } else {
        free(pBuf);
      }
    }
  }
  free(unescaped);

  return rv;
}

static bool statefulCharset(const char *charset)
{
  // HZ, UTF-7 and the CN and KR ISO-2022 variants are no longer in
  // mozilla-central but keeping them here just in case for the benefit of
  // comm-central.
  if (!nsCRT::strncasecmp(charset, "ISO-2022-", sizeof("ISO-2022-")-1) ||
      !nsCRT::strcasecmp(charset, "UTF-7") ||
      !nsCRT::strcasecmp(charset, "HZ-GB-2312"))
    return true;

  return false;
}

nsresult nsTextToSubURI::convertURItoUnicode(const nsAFlatCString &aCharset,
                                             const nsAFlatCString &aURI, 
                                             nsAString &_retval)
{
  // check for 7bit encoding the data may not be ASCII after we decode
  bool isStatefulCharset = statefulCharset(aCharset.get());

  if (!isStatefulCharset) {
    if (IsASCII(aURI)) {
      CopyASCIItoUTF16(aURI, _retval);
      return NS_OK;
    }
    if (IsUTF8(aURI)) {
      CopyUTF8toUTF16(aURI, _retval);
      return NS_OK;
    }
  }

  // empty charset could indicate UTF-8, but aURI turns out not to be UTF-8.
  NS_ENSURE_FALSE(aCharset.IsEmpty(), NS_ERROR_INVALID_ARG);

  nsAutoCString encoding;
  if (!EncodingUtils::FindEncodingForLabelNoReplacement(aCharset, encoding)) {
    return NS_ERROR_UCONV_NOCONV;
  }
  nsCOMPtr<nsIUnicodeDecoder> unicodeDecoder =
    EncodingUtils::DecoderForEncoding(encoding);

  unicodeDecoder->SetInputErrorBehavior(nsIUnicodeDecoder::kOnError_Signal);

  int32_t srcLen = aURI.Length();
  int32_t dstLen;
  nsresult rv = unicodeDecoder->GetMaxLength(aURI.get(), srcLen, &dstLen);
  NS_ENSURE_SUCCESS(rv, rv);

  char16_t *ustr = (char16_t *) moz_xmalloc(dstLen * sizeof(char16_t));
  NS_ENSURE_TRUE(ustr, NS_ERROR_OUT_OF_MEMORY);

  rv = unicodeDecoder->Convert(aURI.get(), &srcLen, ustr, &dstLen);

  if (NS_SUCCEEDED(rv))
    _retval.Assign(ustr, dstLen);
  
  free(ustr);

  return rv;
}

NS_IMETHODIMP  nsTextToSubURI::UnEscapeURIForUI(const nsACString & aCharset, 
                                                const nsACString &aURIFragment, 
                                                nsAString &_retval)
{
  nsAutoCString unescapedSpec;
  // skip control octets (0x00 - 0x1f and 0x7f) when unescaping
  NS_UnescapeURL(PromiseFlatCString(aURIFragment), 
                 esc_SkipControl | esc_AlwaysCopy, unescapedSpec);

  // in case of failure, return escaped URI
  // Test for != NS_OK rather than NS_FAILED, because incomplete multi-byte
  // sequences are also considered failure in this context
  if (convertURItoUnicode(
                PromiseFlatCString(aCharset), unescapedSpec, _retval)
      != NS_OK) {
    // assume UTF-8 instead of ASCII  because hostname (IDN) may be in UTF-8
    CopyUTF8toUTF16(aURIFragment, _retval);
  }

  // If there are any characters that are unsafe for URIs, reescape those.
  if (mUnsafeChars.IsEmpty()) {
    nsAdoptingString blacklist;
    nsresult rv = mozilla::Preferences::GetString("network.IDN.blacklist_chars",
                                                  &blacklist);
    if (NS_SUCCEEDED(rv)) {
      nsAString& chars = blacklist;
      // we allow SPACE and IDEOGRAPHIC SPACE in this method
      chars.StripChars(u" \u3000");
      mUnsafeChars.AppendElements(static_cast<const char16_t*>(chars.Data()),
                                  chars.Length());
    } else {
      NS_WARNING("Failed to get the 'network.IDN.blacklist_chars' preference");
    }
    // We check IsEmpty() intentionally here because an empty (or just spaces)
    // pref value is likely a mistake/error of some sort.
    if (mUnsafeChars.IsEmpty()) {
      mUnsafeChars.AppendElements(sNetworkIDNBlacklistChars,
                                  mozilla::ArrayLength(sNetworkIDNBlacklistChars));
    }
    mUnsafeChars.Sort();
  }
  const nsPromiseFlatString& unescapedResult = PromiseFlatString(_retval);
  nsString reescapedSpec;
  _retval = NS_EscapeURL(unescapedResult, mUnsafeChars, reescapedSpec);

  return NS_OK;
}

NS_IMETHODIMP
nsTextToSubURI::UnEscapeNonAsciiURI(const nsACString& aCharset,
                                    const nsACString& aURIFragment,
                                    nsAString& _retval)
{
  nsAutoCString unescapedSpec;
  NS_UnescapeURL(PromiseFlatCString(aURIFragment),
                 esc_AlwaysCopy | esc_OnlyNonASCII, unescapedSpec);
  // leave the URI as it is if it's not UTF-8 and aCharset is not a ASCII
  // superset since converting "http:" with such an encoding is always a bad
  // idea.
  if (!IsUTF8(unescapedSpec) && 
      (aCharset.LowerCaseEqualsLiteral("utf-16") ||
       aCharset.LowerCaseEqualsLiteral("utf-16be") ||
       aCharset.LowerCaseEqualsLiteral("utf-16le") ||
       aCharset.LowerCaseEqualsLiteral("utf-7") ||
       aCharset.LowerCaseEqualsLiteral("x-imap4-modified-utf7"))){
    CopyASCIItoUTF16(aURIFragment, _retval);
    return NS_OK;
  }

  nsresult rv = convertURItoUnicode(PromiseFlatCString(aCharset),
                                    unescapedSpec, _retval);
  // NS_OK_UDEC_MOREINPUT is a success code, so caller can't catch the error
  // if the string ends with a valid (but incomplete) sequence.
  return rv == NS_OK_UDEC_MOREINPUT ? NS_ERROR_UDEC_ILLEGALINPUT : rv;
}

//----------------------------------------------------------------------