summaryrefslogtreecommitdiff
path: root/core/fpdfapi/font/fpdf_font.cpp
blob: 4702947fd3f094e68a72cf353646c70f052cf5d4 (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
// Copyright 2014 PDFium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.

// Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com

#include "core/fpdfapi/font/font_int.h"

#include <memory>
#include <utility>

#include "core/fpdfapi/cpdf_modulemgr.h"
#include "core/fpdfapi/page/cpdf_form.h"
#include "core/fpdfapi/page/cpdf_pagemodule.h"
#include "core/fpdfapi/page/pageint.h"
#include "core/fpdfapi/parser/cpdf_array.h"
#include "core/fpdfapi/parser/cpdf_dictionary.h"
#include "core/fpdfapi/parser/cpdf_document.h"
#include "core/fpdfapi/parser/cpdf_name.h"
#include "core/fpdfapi/parser/cpdf_number.h"
#include "core/fpdfapi/parser/cpdf_simple_parser.h"
#include "core/fpdfapi/parser/cpdf_stream_acc.h"
#include "core/fxcrt/fx_extension.h"
#include "core/fxcrt/fx_safe_types.h"
#include "core/fxge/fx_freetype.h"
#include "third_party/base/numerics/safe_conversions.h"
#include "third_party/base/ptr_util.h"
#include "third_party/base/stl_util.h"

int TT2PDF(int m, FXFT_Face face) {
  int upm = FXFT_Get_Face_UnitsPerEM(face);
  if (upm == 0)
    return m;
  return pdfium::base::checked_cast<int>(
      (static_cast<double>(m) * 1000 + upm / 2) / upm);
}

bool FT_UseTTCharmap(FXFT_Face face, int platform_id, int encoding_id) {
  auto** pCharMap = FXFT_Get_Face_Charmaps(face);
  for (int i = 0; i < FXFT_Get_Face_CharmapCount(face); i++) {
    if (FXFT_Get_Charmap_PlatformID(pCharMap[i]) == platform_id &&
        FXFT_Get_Charmap_EncodingID(pCharMap[i]) == encoding_id) {
      FXFT_Set_Charmap(face, pCharMap[i]);
      return true;
    }
  }
  return false;
}

CFX_StockFontArray::CFX_StockFontArray() {}

CFX_StockFontArray::~CFX_StockFontArray() {
  for (size_t i = 0; i < FX_ArraySize(m_StockFonts); ++i) {
    if (m_StockFonts[i])
      delete m_StockFonts[i]->GetFontDict();
  }
}

CPDF_Font* CFX_StockFontArray::GetFont(uint32_t index) const {
  if (index >= FX_ArraySize(m_StockFonts))
    return nullptr;
  return m_StockFonts[index].get();
}

CPDF_Font* CFX_StockFontArray::SetFont(uint32_t index,
                                       std::unique_ptr<CPDF_Font> pFont) {
  CPDF_Font* result = pFont.get();
  if (index < FX_ArraySize(m_StockFonts))
    m_StockFonts[index] = std::move(pFont);
  return result;
}

CPDF_FontGlobals::CPDF_FontGlobals() {
  memset(m_EmbeddedCharsets, 0, sizeof(m_EmbeddedCharsets));
  memset(m_EmbeddedToUnicodes, 0, sizeof(m_EmbeddedToUnicodes));
}

CPDF_FontGlobals::~CPDF_FontGlobals() {}

CPDF_Font* CPDF_FontGlobals::Find(CPDF_Document* pDoc, uint32_t index) {
  auto it = m_StockMap.find(pDoc);
  if (it == m_StockMap.end())
    return nullptr;
  return it->second ? it->second->GetFont(index) : nullptr;
}

CPDF_Font* CPDF_FontGlobals::Set(CPDF_Document* pDoc,
                                 uint32_t index,
                                 std::unique_ptr<CPDF_Font> pFont) {
  if (!pdfium::ContainsKey(m_StockMap, pDoc))
    m_StockMap[pDoc] = pdfium::MakeUnique<CFX_StockFontArray>();
  return m_StockMap[pDoc]->SetFont(index, std::move(pFont));
}

void CPDF_FontGlobals::Clear(CPDF_Document* pDoc) {
  m_StockMap.erase(pDoc);
}

CFX_WideString CPDF_ToUnicodeMap::Lookup(uint32_t charcode) const {
  auto it = m_Map.find(charcode);
  if (it != m_Map.end()) {
    uint32_t value = it->second;
    wchar_t unicode = (wchar_t)(value & 0xffff);
    if (unicode != 0xffff) {
      return unicode;
    }
    const wchar_t* buf = m_MultiCharBuf.GetBuffer();
    uint32_t buf_len = m_MultiCharBuf.GetLength();
    if (!buf || buf_len == 0) {
      return CFX_WideString();
    }
    uint32_t index = value >> 16;
    if (index >= buf_len) {
      return CFX_WideString();
    }
    uint32_t len = buf[index];
    if (index + len < index || index + len >= buf_len) {
      return CFX_WideString();
    }
    return CFX_WideString(buf + index + 1, len);
  }
  if (m_pBaseMap) {
    return m_pBaseMap->UnicodeFromCID((uint16_t)charcode);
  }
  return CFX_WideString();
}

uint32_t CPDF_ToUnicodeMap::ReverseLookup(wchar_t unicode) const {
  for (const auto& pair : m_Map) {
    if (pair.second == static_cast<uint32_t>(unicode))
      return pair.first;
  }
  return 0;
}

// Static.
uint32_t CPDF_ToUnicodeMap::StringToCode(const CFX_ByteStringC& str) {
  int len = str.GetLength();
  if (len == 0)
    return 0;

  uint32_t result = 0;
  if (str[0] == '<') {
    for (int i = 1; i < len && std::isxdigit(str[i]); ++i)
      result = result * 16 + FXSYS_HexCharToInt(str.CharAt(i));
    return result;
  }

  for (int i = 0; i < len && std::isdigit(str[i]); ++i)
    result = result * 10 + FXSYS_DecimalCharToInt(str.CharAt(i));

  return result;
}

static CFX_WideString StringDataAdd(CFX_WideString str) {
  CFX_WideString ret;
  int len = str.GetLength();
  wchar_t value = 1;
  for (int i = len - 1; i >= 0; --i) {
    wchar_t ch = str[i] + value;
    if (ch < str[i]) {
      ret.Insert(0, 0);
    } else {
      ret.Insert(0, ch);
      value = 0;
    }
  }
  if (value) {
    ret.Insert(0, value);
  }
  return ret;
}

// Static.
CFX_WideString CPDF_ToUnicodeMap::StringToWideString(
    const CFX_ByteStringC& str) {
  int len = str.GetLength();
  if (len == 0)
    return CFX_WideString();

  CFX_WideString result;
  if (str[0] == '<') {
    int byte_pos = 0;
    wchar_t ch = 0;
    for (int i = 1; i < len && std::isxdigit(str[i]); ++i) {
      ch = ch * 16 + FXSYS_HexCharToInt(str[i]);
      byte_pos++;
      if (byte_pos == 4) {
        result += ch;
        byte_pos = 0;
        ch = 0;
      }
    }
    return result;
  }
  return result;
}

CPDF_ToUnicodeMap::CPDF_ToUnicodeMap() : m_pBaseMap(nullptr) {}

CPDF_ToUnicodeMap::~CPDF_ToUnicodeMap() {}

uint32_t CPDF_ToUnicodeMap::GetUnicode() {
  FX_SAFE_UINT32 uni = m_MultiCharBuf.GetLength();
  uni = uni * 0x10000 + 0xffff;
  return uni.ValueOrDefault(0);
}

void CPDF_ToUnicodeMap::Load(CPDF_Stream* pStream) {
  CIDSet cid_set = CIDSET_UNKNOWN;
  auto pAcc = pdfium::MakeRetain<CPDF_StreamAcc>(pStream);
  pAcc->LoadAllData(false);
  CPDF_SimpleParser parser(pAcc->GetData(), pAcc->GetSize());
  while (1) {
    CFX_ByteStringC word = parser.GetWord();
    if (word.IsEmpty()) {
      break;
    }
    if (word == "beginbfchar") {
      while (1) {
        word = parser.GetWord();
        if (word.IsEmpty() || word == "endbfchar") {
          break;
        }
        uint32_t srccode = StringToCode(word);
        word = parser.GetWord();
        CFX_WideString destcode = StringToWideString(word);
        int len = destcode.GetLength();
        if (len == 0) {
          continue;
        }
        if (len == 1) {
          m_Map[srccode] = destcode.GetAt(0);
        } else {
          m_Map[srccode] = GetUnicode();
          m_MultiCharBuf.AppendChar(destcode.GetLength());
          m_MultiCharBuf << destcode;
        }
      }
    } else if (word == "beginbfrange") {
      while (1) {
        CFX_ByteString low, high;
        low = parser.GetWord();
        if (low.IsEmpty() || low == "endbfrange") {
          break;
        }
        high = parser.GetWord();
        uint32_t lowcode = StringToCode(low.AsStringC());
        uint32_t highcode =
            (lowcode & 0xffffff00) | (StringToCode(high.AsStringC()) & 0xff);
        if (highcode == (uint32_t)-1) {
          break;
        }
        CFX_ByteString start(parser.GetWord());
        if (start == "[") {
          for (uint32_t code = lowcode; code <= highcode; code++) {
            CFX_ByteString dest(parser.GetWord());
            CFX_WideString destcode = StringToWideString(dest.AsStringC());
            int len = destcode.GetLength();
            if (len == 0) {
              continue;
            }
            if (len == 1) {
              m_Map[code] = destcode.GetAt(0);
            } else {
              m_Map[code] = GetUnicode();
              m_MultiCharBuf.AppendChar(destcode.GetLength());
              m_MultiCharBuf << destcode;
            }
          }
          parser.GetWord();
        } else {
          CFX_WideString destcode = StringToWideString(start.AsStringC());
          int len = destcode.GetLength();
          uint32_t value = 0;
          if (len == 1) {
            value = StringToCode(start.AsStringC());
            for (uint32_t code = lowcode; code <= highcode; code++) {
              m_Map[code] = value++;
            }
          } else {
            for (uint32_t code = lowcode; code <= highcode; code++) {
              CFX_WideString retcode;
              if (code == lowcode) {
                retcode = destcode;
              } else {
                retcode = StringDataAdd(destcode);
              }
              m_Map[code] = GetUnicode();
              m_MultiCharBuf.AppendChar(retcode.GetLength());
              m_MultiCharBuf << retcode;
              destcode = retcode;
            }
          }
        }
      }
    } else if (word == "/Adobe-Korea1-UCS2") {
      cid_set = CIDSET_KOREA1;
    } else if (word == "/Adobe-Japan1-UCS2") {
      cid_set = CIDSET_JAPAN1;
    } else if (word == "/Adobe-CNS1-UCS2") {
      cid_set = CIDSET_CNS1;
    } else if (word == "/Adobe-GB1-UCS2") {
      cid_set = CIDSET_GB1;
    }
  }
  if (cid_set) {
    m_pBaseMap = CPDF_ModuleMgr::Get()
                     ->GetPageModule()
                     ->GetFontGlobals()
                     ->m_CMapManager.GetCID2UnicodeMap(cid_set, false);
  } else {
    m_pBaseMap = nullptr;
  }
}