summaryrefslogtreecommitdiffstats
path: root/netwerk/streamconv/converters/nsDirIndexParser.cpp
blob: 1f4bc78cb00b81c415828c4cc574b0d5dc75334c (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
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
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
/* -*- Mode: C++; tab-width: 2; 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/. */

/* This parsing code originally lived in xpfe/components/directory/ - bbaetz */

#include "mozilla/ArrayUtils.h"

#include "prprf.h"

#include "nsDirIndexParser.h"
#include "nsEscape.h"
#include "nsIInputStream.h"
#include "nsCRT.h"
#include "mozilla/dom/FallbackEncoding.h"
#include "nsITextToSubURI.h"
#include "nsIDirIndex.h"
#include "nsServiceManagerUtils.h"

using namespace mozilla;

NS_IMPL_ISUPPORTS(nsDirIndexParser,
                  nsIRequestObserver,
                  nsIStreamListener,
                  nsIDirIndexParser)

nsDirIndexParser::nsDirIndexParser() {
}

nsresult
nsDirIndexParser::Init() {
  mLineStart = 0;
  mHasDescription = false;
  mFormat[0] = -1;
  mozilla::dom::FallbackEncoding::FromLocale(mEncoding);
 
  nsresult rv;
  // XXX not threadsafe
  if (gRefCntParser++ == 0)
    rv = CallGetService(NS_ITEXTTOSUBURI_CONTRACTID, &gTextToSubURI);
  else
    rv = NS_OK;

  return rv;
}

nsDirIndexParser::~nsDirIndexParser() {
  // XXX not threadsafe
  if (--gRefCntParser == 0) {
    NS_IF_RELEASE(gTextToSubURI);
  }
}

NS_IMETHODIMP
nsDirIndexParser::SetListener(nsIDirIndexListener* aListener) {
  mListener = aListener;
  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::GetListener(nsIDirIndexListener** aListener) {
  NS_IF_ADDREF(*aListener = mListener.get());
  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::GetComment(char** aComment) {
  *aComment = ToNewCString(mComment);

  if (!*aComment)
    return NS_ERROR_OUT_OF_MEMORY;
  
  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::SetEncoding(const char* aEncoding) {
  mEncoding.Assign(aEncoding);
  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::GetEncoding(char** aEncoding) {
  *aEncoding = ToNewCString(mEncoding);

  if (!*aEncoding)
    return NS_ERROR_OUT_OF_MEMORY;

  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::OnStartRequest(nsIRequest* aRequest, nsISupports* aCtxt) {
  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::OnStopRequest(nsIRequest *aRequest, nsISupports *aCtxt,
                                nsresult aStatusCode) {
  // Finish up
  if (mBuf.Length() > (uint32_t) mLineStart) {
    ProcessData(aRequest, aCtxt);
  }

  return NS_OK;
}

nsDirIndexParser::Field
nsDirIndexParser::gFieldTable[] = {
  { "Filename", FIELD_FILENAME },
  { "Description", FIELD_DESCRIPTION },
  { "Content-Length", FIELD_CONTENTLENGTH },
  { "Last-Modified", FIELD_LASTMODIFIED },
  { "Content-Type", FIELD_CONTENTTYPE },
  { "File-Type", FIELD_FILETYPE },
  { nullptr, FIELD_UNKNOWN }
};

nsrefcnt nsDirIndexParser::gRefCntParser = 0;
nsITextToSubURI *nsDirIndexParser::gTextToSubURI;

nsresult
nsDirIndexParser::ParseFormat(const char* aFormatStr)
{
  // Parse a "200" format line, and remember the fields and their
  // ordering in mFormat. Multiple 200 lines stomp on each other.
  unsigned int formatNum = 0;
  mFormat[0] = -1;

  do {
    while (*aFormatStr && nsCRT::IsAsciiSpace(char16_t(*aFormatStr)))
      ++aFormatStr;
    
    if (! *aFormatStr)
      break;

    nsAutoCString name;
    int32_t     len = 0;
    while (aFormatStr[len] && !nsCRT::IsAsciiSpace(char16_t(aFormatStr[len])))
      ++len;
    name.SetCapacity(len + 1);
    name.Append(aFormatStr, len);
    aFormatStr += len;
    
    // Okay, we're gonna monkey with the nsStr. Bold!
    name.SetLength(nsUnescapeCount(name.BeginWriting()));

    // All tokens are case-insensitive - http://www.mozilla.org/projects/netlib/dirindexformat.html
    if (name.LowerCaseEqualsLiteral("description"))
      mHasDescription = true;
    
    for (Field* i = gFieldTable; i->mName; ++i) {
      if (name.EqualsIgnoreCase(i->mName)) {
        mFormat[formatNum] = i->mType;
        mFormat[++formatNum] = -1;
        break;
      }
    }

  } while (*aFormatStr && (formatNum < (ArrayLength(mFormat)-1)));
  
  return NS_OK;
}

nsresult
nsDirIndexParser::ParseData(nsIDirIndex *aIdx, char* aDataStr, int32_t aLineLen)
{
  // Parse a "201" data line, using the field ordering specified in
  // mFormat.

  if(mFormat[0] == -1) {
    // Ignore if we haven't seen a format yet.
    return NS_OK;
  }

  nsresult rv = NS_OK;
  nsAutoCString filename;
  int32_t lineLen = aLineLen;

  for (int32_t i = 0; mFormat[i] != -1; ++i) {
    // If we've exhausted the data before we run out of fields, just bail.
    if (!*aDataStr || (lineLen < 1)) {
      return NS_OK;
    }

    while ((lineLen > 0) && nsCRT::IsAsciiSpace(*aDataStr)) {
      ++aDataStr;
      --lineLen;
    }

    if (lineLen < 1) {
      // invalid format, bail
      return NS_OK;
    }

    char    *value = aDataStr;
    if (*aDataStr == '"' || *aDataStr == '\'') {
      // it's a quoted string. snarf everything up to the next quote character
      const char quotechar = *(aDataStr++);
      lineLen--;
      ++value;
      while ((lineLen > 0) && *aDataStr != quotechar) {
        ++aDataStr;
        --lineLen;
      }
      if (lineLen > 0) {
        *aDataStr++ = '\0';
        --lineLen;
      }

      if (!lineLen) {
        // invalid format, bail
        return NS_OK;
      }
    } else {
      // it's unquoted. snarf until we see whitespace.
      value = aDataStr;
      while ((lineLen > 0) && (!nsCRT::IsAsciiSpace(*aDataStr))) {
        ++aDataStr;
        --lineLen;
      }
      if (lineLen > 0) {
        *aDataStr++ = '\0';
        --lineLen;
      }
      // even if we ran out of line length here, there's still a trailing zero
      // byte afterwards
    }

    fieldType t = fieldType(mFormat[i]);
    switch (t) {
    case FIELD_FILENAME: {
      // don't unescape at this point, so that UnEscapeAndConvert() can
      filename = value;
      
      bool    success = false;
      
      nsAutoString entryuri;
      
      if (gTextToSubURI) {
        char16_t   *result = nullptr;
        if (NS_SUCCEEDED(rv = gTextToSubURI->UnEscapeAndConvert(mEncoding.get(), filename.get(),
                                                                &result)) && (result)) {
          if (*result) {
            aIdx->SetLocation(filename.get());
            if (!mHasDescription)
              aIdx->SetDescription(result);
            success = true;
          }
          free(result);
        } else {
          NS_WARNING("UnEscapeAndConvert error");
        }
      }
      
      if (!success) {
        // if unsuccessfully at charset conversion, then
        // just fallback to unescape'ing in-place
        // XXX - this shouldn't be using UTF8, should it?
        // when can we fail to get the service, anyway? - bbaetz
        aIdx->SetLocation(filename.get());
        if (!mHasDescription) {
          aIdx->SetDescription(NS_ConvertUTF8toUTF16(value).get());
        }
      }
    }
      break;
    case FIELD_DESCRIPTION:
      nsUnescape(value);
      aIdx->SetDescription(NS_ConvertUTF8toUTF16(value).get());
      break;
    case FIELD_CONTENTLENGTH:
      {
        int64_t len;
        int32_t status = PR_sscanf(value, "%lld", &len);
        if (status == 1)
          aIdx->SetSize(len);
        else
          aIdx->SetSize(UINT64_MAX); // UINT64_MAX means unknown
      }
      break;
    case FIELD_LASTMODIFIED:
      {
        PRTime tm;
        nsUnescape(value);
        if (PR_ParseTimeString(value, false, &tm) == PR_SUCCESS) {
          aIdx->SetLastModified(tm);
        }
      }
      break;
    case FIELD_CONTENTTYPE:
      aIdx->SetContentType(value);
      break;
    case FIELD_FILETYPE:
      // unescape in-place
      nsUnescape(value);
      if (!nsCRT::strcasecmp(value, "directory")) {
        aIdx->SetType(nsIDirIndex::TYPE_DIRECTORY);
      } else if (!nsCRT::strcasecmp(value, "file")) {
        aIdx->SetType(nsIDirIndex::TYPE_FILE);
      } else if (!nsCRT::strcasecmp(value, "symbolic-link")) {
        aIdx->SetType(nsIDirIndex::TYPE_SYMLINK);
      } else {
        aIdx->SetType(nsIDirIndex::TYPE_UNKNOWN);
      }
      break;
    case FIELD_UNKNOWN:
      // ignore
      break;
    }
  }

  return NS_OK;
}

NS_IMETHODIMP
nsDirIndexParser::OnDataAvailable(nsIRequest *aRequest, nsISupports *aCtxt,
                                  nsIInputStream *aStream,
                                  uint64_t aSourceOffset,
                                  uint32_t aCount) {
  if (aCount < 1)
    return NS_OK;
  
  int32_t len = mBuf.Length();
  
  // Ensure that our mBuf has capacity to hold the data we're about to
  // read.
  if (!mBuf.SetLength(len + aCount, fallible))
    return NS_ERROR_OUT_OF_MEMORY;

  // Now read the data into our buffer.
  nsresult rv;
  uint32_t count;
  rv = aStream->Read(mBuf.BeginWriting() + len, aCount, &count);
  if (NS_FAILED(rv)) return rv;

  // Set the string's length according to the amount of data we've read.
  // Note: we know this to work on nsCString. This isn't guaranteed to
  //       work on other strings.
  mBuf.SetLength(len + count);

  return ProcessData(aRequest, aCtxt);
}

nsresult
nsDirIndexParser::ProcessData(nsIRequest *aRequest, nsISupports *aCtxt) {
  if (!mListener)
    return NS_ERROR_FAILURE;
  
  int32_t     numItems = 0;
  
  while(true) {
    ++numItems;
    
    int32_t             eol = mBuf.FindCharInSet("\n\r", mLineStart);
    if (eol < 0)        break;
    mBuf.SetCharAt(char16_t('\0'), eol);
    
    const char  *line = mBuf.get() + mLineStart;
    
    int32_t lineLen = eol - mLineStart;
    mLineStart = eol + 1;
    
    if (lineLen >= 4) {
      nsresult  rv;
      const char        *buf = line;
      
      if (buf[0] == '1') {
        if (buf[1] == '0') {
          if (buf[2] == '0' && buf[3] == ':') {
            // 100. Human-readable comment line. Ignore
          } else if (buf[2] == '1' && buf[3] == ':') {
            // 101. Human-readable information line.
            mComment.Append(buf + 4);

            char    *value = ((char *)buf) + 4;
            nsUnescape(value);
            mListener->OnInformationAvailable(aRequest, aCtxt, NS_ConvertUTF8toUTF16(value));

          } else if (buf[2] == '2' && buf[3] == ':') {
            // 102. Human-readable information line, HTML.
            mComment.Append(buf + 4);
          }
        }
      } else if (buf[0] == '2') {
        if (buf[1] == '0') {
          if (buf[2] == '0' && buf[3] == ':') {
            // 200. Define field names
            rv = ParseFormat(buf + 4);
            if (NS_FAILED(rv)) {
              return rv;
            }
          } else if (buf[2] == '1' && buf[3] == ':') {
            // 201. Field data
            nsCOMPtr<nsIDirIndex> idx = do_CreateInstance("@mozilla.org/dirIndex;1",&rv);
            if (NS_FAILED(rv))
              return rv;
            
            rv = ParseData(idx, ((char *)buf) + 4, lineLen - 4);
            if (NS_FAILED(rv)) {
              return rv;
            }

            mListener->OnIndexAvailable(aRequest, aCtxt, idx);
          }
        }
      } else if (buf[0] == '3') {
        if (buf[1] == '0') {
          if (buf[2] == '0' && buf[3] == ':') {
            // 300. Self-referring URL
          } else if (buf[2] == '1' && buf[3] == ':') {
            // 301. OUR EXTENSION - encoding
            int i = 4;
            while (buf[i] && nsCRT::IsAsciiSpace(buf[i]))
              ++i;
            
            if (buf[i])
              SetEncoding(buf+i);
          }
        }
      }
    }
  }
  
  return NS_OK;
}