aboutsummaryrefslogtreecommitdiffhomepage
path: root/src/pdf/SkPDFMetadata.cpp
blob: ee5c19bba4bb9236bee6a4f4b76ed189ef0bdbde (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
/*
 * Copyright 2015 Google Inc.
 *
 * Use of this source code is governed by a BSD-style license that can be
 * found in the LICENSE file.
 */

#include "SkMD5.h"
#include "SkMilestone.h"
#include "SkPDFMetadata.h"
#include "SkPDFTypes.h"
#include <utility>

#define SKPDF_STRING(X) SKPDF_STRING_IMPL(X)
#define SKPDF_STRING_IMPL(X) #X
#define SKPDF_PRODUCER "Skia/PDF m" SKPDF_STRING(SK_MILESTONE)
#define SKPDF_CUSTOM_PRODUCER_KEY "ProductionLibrary"

static SkString pdf_date(const SkTime::DateTime& dt) {
    int timeZoneMinutes = SkToInt(dt.fTimeZoneMinutes);
    char timezoneSign = timeZoneMinutes >= 0 ? '+' : '-';
    int timeZoneHours = SkTAbs(timeZoneMinutes) / 60;
    timeZoneMinutes = SkTAbs(timeZoneMinutes) % 60;
    return SkStringPrintf(
            "D:%04u%02u%02u%02u%02u%02u%c%02d'%02d'",
            static_cast<unsigned>(dt.fYear), static_cast<unsigned>(dt.fMonth),
            static_cast<unsigned>(dt.fDay), static_cast<unsigned>(dt.fHour),
            static_cast<unsigned>(dt.fMinute),
            static_cast<unsigned>(dt.fSecond), timezoneSign, timeZoneHours,
            timeZoneMinutes);
}

namespace {
static const struct {
    const char* const key;
    SkString SkDocument::PDFMetadata::*const valuePtr;
} gMetadataKeys[] = {
        {"Title", &SkDocument::PDFMetadata::fTitle},
        {"Author", &SkDocument::PDFMetadata::fAuthor},
        {"Subject", &SkDocument::PDFMetadata::fSubject},
        {"Keywords", &SkDocument::PDFMetadata::fKeywords},
        {"Creator", &SkDocument::PDFMetadata::fCreator},
};
}  // namespace

sk_sp<SkPDFObject> SkPDFMetadata::MakeDocumentInformationDict(
        const SkDocument::PDFMetadata& metadata) {
    auto dict = sk_make_sp<SkPDFDict>();
    for (const auto keyValuePtr : gMetadataKeys) {
        const SkString& value = metadata.*(keyValuePtr.valuePtr);
        if (value.size() > 0) {
            dict->insertString(keyValuePtr.key, value);
        }
    }
    if (metadata.fProducer.isEmpty()) {
        dict->insertString("Producer", SKPDF_PRODUCER);
    } else {
        dict->insertString("Producer", metadata.fProducer);
        dict->insertString(SKPDF_CUSTOM_PRODUCER_KEY, SKPDF_PRODUCER);
    }
    if (metadata.fCreation.fEnabled) {
        dict->insertString("CreationDate",
                           pdf_date(metadata.fCreation.fDateTime));
    }
    if (metadata.fModified.fEnabled) {
        dict->insertString("ModDate", pdf_date(metadata.fModified.fDateTime));
    }
    return dict;
}

SkPDFMetadata::UUID SkPDFMetadata::CreateUUID(
        const SkDocument::PDFMetadata& metadata) {
    // The main requirement is for the UUID to be unique; the exact
    // format of the data that will be hashed is not important.
    SkMD5 md5;
    const char uuidNamespace[] = "org.skia.pdf\n";
    md5.write(uuidNamespace, strlen(uuidNamespace));
    double msec = SkTime::GetMSecs();
    md5.write(&msec, sizeof(msec));
    SkTime::DateTime dateTime;
    SkTime::GetDateTime(&dateTime);
    md5.write(&dateTime, sizeof(dateTime));
    if (metadata.fCreation.fEnabled) {
        md5.write(&metadata.fCreation.fDateTime,
                  sizeof(metadata.fCreation.fDateTime));
    }
    if (metadata.fModified.fEnabled) {
        md5.write(&metadata.fModified.fDateTime,
                  sizeof(metadata.fModified.fDateTime));
    }

    for (const auto keyValuePtr : gMetadataKeys) {
        md5.write(keyValuePtr.key, strlen(keyValuePtr.key));
        md5.write("\037", 1);
        const SkString& value = metadata.*(keyValuePtr.valuePtr);
        md5.write(value.c_str(), value.size());
        md5.write("\036", 1);
    }
    SkMD5::Digest digest;
    md5.finish(digest);
    // See RFC 4122, page 6-7.
    digest.data[6] = (digest.data[6] & 0x0F) | 0x30;
    digest.data[8] = (digest.data[6] & 0x3F) | 0x80;
    static_assert(sizeof(digest) == sizeof(UUID), "uuid_size");
    SkPDFMetadata::UUID uuid;
    memcpy(&uuid, &digest, sizeof(digest));
    return uuid;
}

sk_sp<SkPDFObject> SkPDFMetadata::MakePdfId(const UUID& doc,
                                            const UUID& instance) {
    // /ID [ <81b14aafa313db63dbd6f981e49f94f4>
    //       <81b14aafa313db63dbd6f981e49f94f4> ]
    auto array = sk_make_sp<SkPDFArray>();
    static_assert(sizeof(SkPDFMetadata::UUID) == 16, "uuid_size");
    array->appendString(
            SkString(reinterpret_cast<const char*>(&doc), sizeof(UUID)));
    array->appendString(
            SkString(reinterpret_cast<const char*>(&instance), sizeof(UUID)));
    return array;
}

#define HEXIFY(INPUT_PTR, OUTPUT_PTR, HEX_STRING, BYTE_COUNT) \
    do {                                                      \
        for (int i = 0; i < (BYTE_COUNT); ++i) {              \
            uint8_t value = *(INPUT_PTR)++;                   \
            *(OUTPUT_PTR)++ = (HEX_STRING)[value >> 4];       \
            *(OUTPUT_PTR)++ = (HEX_STRING)[value & 0xF];      \
        }                                                     \
    } while (false)
static SkString uuid_to_string(const SkPDFMetadata::UUID& uuid) {
    //  8-4-4-4-12
    char buffer[36];  // [32 + 4]
    static const char gHex[] = "0123456789abcdef";
    SkASSERT(strlen(gHex) == 16);
    char* ptr = buffer;
    const uint8_t* data = uuid.fData;
    HEXIFY(data, ptr, gHex, 4);
    *ptr++ = '-';
    HEXIFY(data, ptr, gHex, 2);
    *ptr++ = '-';
    HEXIFY(data, ptr, gHex, 2);
    *ptr++ = '-';
    HEXIFY(data, ptr, gHex, 2);
    *ptr++ = '-';
    HEXIFY(data, ptr, gHex, 6);
    SkASSERT(ptr == buffer + 36);
    SkASSERT(data == uuid.fData + 16);
    return SkString(buffer, 36);
}
#undef HEXIFY

namespace {
class PDFXMLObject final : public SkPDFObject {
public:
    PDFXMLObject(SkString xml) : fXML(std::move(xml)) {}
    void emitObject(SkWStream* stream,
                    const SkPDFObjNumMap& omap) const override {
        SkPDFDict dict("Metadata");
        dict.insertName("Subtype", "XML");
        dict.insertInt("Length", fXML.size());
        dict.emitObject(stream, omap);
        static const char streamBegin[] = " stream\n";
        stream->write(streamBegin, strlen(streamBegin));
        // Do not compress this.  The standard requires that a
        // program that does not understand PDF can grep for
        // "<?xpacket" and extract the entire XML.
        stream->write(fXML.c_str(), fXML.size());
        static const char streamEnd[] = "\nendstream";
        stream->write(streamEnd, strlen(streamEnd));
    }

private:
    const SkString fXML;
};
}  // namespace

static int count_xml_escape_size(const SkString& input) {
    int extra = 0;
    for (size_t i = 0; i < input.size(); ++i) {
        if (input[i] == '&') {
            extra += 4;  // strlen("&amp;") - strlen("&")
        } else if (input[i] == '<') {
            extra += 3;  // strlen("&lt;") - strlen("<")
        }
    }
    return extra;
}

const SkString escape_xml(const SkString& input,
                          const char* before = nullptr,
                          const char* after = nullptr) {
    if (input.size() == 0) {
        return input;
    }
    // "&" --> "&amp;" and  "<" --> "&lt;"
    // text is assumed to be in UTF-8
    // all strings are xml content, not attribute values.
    size_t beforeLen = before ? strlen(before) : 0;
    size_t afterLen = after ? strlen(after) : 0;
    int extra = count_xml_escape_size(input);
    SkString output(input.size() + extra + beforeLen + afterLen);
    char* out = output.writable_str();
    if (before) {
        strncpy(out, before, beforeLen);
        out += beforeLen;
    }
    static const char kAmp[] = "&amp;";
    static const char kLt[] = "&lt;";
    for (size_t i = 0; i < input.size(); ++i) {
        if (input[i] == '&') {
            strncpy(out, kAmp, strlen(kAmp));
            out += strlen(kAmp);
        } else if (input[i] == '<') {
            strncpy(out, kLt, strlen(kLt));
            out += strlen(kLt);
        } else {
            *out++ = input[i];
        }
    }
    if (after) {
        strncpy(out, after, afterLen);
        out += afterLen;
    }
    // Validate that we haven't written outside of our string.
    SkASSERT(out == &output.writable_str()[output.size()]);
    *out = '\0';
    return output;
}

sk_sp<SkPDFObject> SkPDFMetadata::MakeXMPObject(
        const SkDocument::PDFMetadata& metadata,
        const UUID& doc,
        const UUID& instance) {
    static const char templateString[] =
            "<?xpacket begin=\"\" id=\"W5M0MpCehiHzreSzNTczkc9d\"?>\n"
            "<x:xmpmeta xmlns:x=\"adobe:ns:meta/\"\n"
            " x:xmptk=\"Adobe XMP Core 5.4-c005 78.147326, "
            "2012/08/23-13:03:03\">\n"
            "<rdf:RDF "
            "xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n"
            "<rdf:Description rdf:about=\"\"\n"
            " xmlns:xmp=\"http://ns.adobe.com/xap/1.0/\"\n"
            " xmlns:dc=\"http://purl.org/dc/elements/1.1/\"\n"
            " xmlns:xmpMM=\"http://ns.adobe.com/xap/1.0/mm/\"\n"
            " xmlns:pdf=\"http://ns.adobe.com/pdf/1.3/\"\n"
            " xmlns:pdfaid=\"http://www.aiim.org/pdfa/ns/id/\">\n"
            "<pdfaid:part>2</pdfaid:part>\n"
            "<pdfaid:conformance>B</pdfaid:conformance>\n"
            "%s"  // ModifyDate
            "%s"  // CreateDate
            "%s"  // xmp:CreatorTool
            "<dc:format>application/pdf</dc:format>\n"
            "%s"  // dc:title
            "%s"  // dc:description
            "%s"  // author
            "%s"  // keywords
            "<xmpMM:DocumentID>uuid:%s</xmpMM:DocumentID>\n"
            "<xmpMM:InstanceID>uuid:%s</xmpMM:InstanceID>\n"
            "%s"  // pdf:Producer
            "%s"  // pdf:Keywords
            "</rdf:Description>\n"
            "</rdf:RDF>\n"
            "</x:xmpmeta>\n"  // Note:  the standard suggests 4k of padding.
            "<?xpacket end=\"w\"?>\n";

    SkString creationDate;
    SkString modificationDate;
    if (metadata.fCreation.fEnabled) {
        SkString tmp;
        metadata.fCreation.fDateTime.toISO8601(&tmp);
        SkASSERT(0 == count_xml_escape_size(tmp));
        // YYYY-mm-ddTHH:MM:SS[+|-]ZZ:ZZ; no need to escape
        creationDate = SkStringPrintf("<xmp:CreateDate>%s</xmp:CreateDate>\n",
                                      tmp.c_str());
    }
    if (metadata.fModified.fEnabled) {
        SkString tmp;
        metadata.fModified.fDateTime.toISO8601(&tmp);
        SkASSERT(0 == count_xml_escape_size(tmp));
        modificationDate = SkStringPrintf(
                "<xmp:ModifyDate>%s</xmp:ModifyDate>\n", tmp.c_str());
    }
    SkString title =
            escape_xml(metadata.fTitle,
                       "<dc:title><rdf:Alt><rdf:li xml:lang=\"x-default\">",
                       "</rdf:li></rdf:Alt></dc:title>\n");
    SkString author =
            escape_xml(metadata.fAuthor, "<dc:creator><rdf:Bag><rdf:li>",
                       "</rdf:li></rdf:Bag></dc:creator>\n");
    // TODO: in theory, XMP can support multiple authors.  Split on a delimiter?
    SkString subject = escape_xml(
            metadata.fSubject,
            "<dc:description><rdf:Alt><rdf:li xml:lang=\"x-default\">",
            "</rdf:li></rdf:Alt></dc:description>\n");
    SkString keywords1 =
            escape_xml(metadata.fKeywords, "<dc:subject><rdf:Bag><rdf:li>",
                       "</rdf:li></rdf:Bag></dc:subject>\n");
    SkString keywords2 = escape_xml(metadata.fKeywords, "<pdf:Keywords>",
                                    "</pdf:Keywords>\n");
    // TODO: in theory, keywords can be a list too.

    SkString producer("<pdf:Producer>" SKPDF_PRODUCER "</pdf:Producer>\n");
    if (!metadata.fProducer.isEmpty()) {
        // TODO: register a developer prefix to make
        // <skia:SKPDF_CUSTOM_PRODUCER_KEY> a real XML tag.
        producer = escape_xml(
                metadata.fProducer, "<pdf:Producer>",
                "</pdf:Producer>\n<!-- <skia:" SKPDF_CUSTOM_PRODUCER_KEY ">"
                SKPDF_PRODUCER "</skia:" SKPDF_CUSTOM_PRODUCER_KEY "> -->\n");
    }

    SkString creator = escape_xml(metadata.fCreator, "<xmp:CreatorTool>",
                                  "</xmp:CreatorTool>\n");
    SkString documentID = uuid_to_string(doc);  // no need to escape
    SkASSERT(0 == count_xml_escape_size(documentID));
    SkString instanceID = uuid_to_string(instance);
    SkASSERT(0 == count_xml_escape_size(instanceID));
    return sk_make_sp<PDFXMLObject>(SkStringPrintf(
            templateString, modificationDate.c_str(), creationDate.c_str(),
            creator.c_str(), title.c_str(), subject.c_str(), author.c_str(),
            keywords1.c_str(), documentID.c_str(), instanceID.c_str(),
            producer.c_str(), keywords2.c_str()));
}

#undef SKPDF_CUSTOM_PRODUCER_KEY
#undef SKPDF_PRODUCER
#undef SKPDF_STRING
#undef SKPDF_STRING_IMPL