@codecloud-dev/pdf-lib-plus 1.18.2 → 1.18.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +53 -4
- package/README.zh.md +31 -2
- package/cjs/api/PDFPage.d.ts +12 -0
- package/cjs/api/PDFPage.d.ts.map +1 -1
- package/cjs/api/PDFPage.js +18 -0
- package/cjs/api/PDFPage.js.map +1 -1
- package/cjs/api/index.d.ts +1 -0
- package/cjs/api/index.d.ts.map +1 -1
- package/cjs/api/index.js +1 -0
- package/cjs/api/index.js.map +1 -1
- package/cjs/api/rotations.d.ts +1 -1
- package/cjs/api/text_extraction.d.ts +20 -0
- package/cjs/api/text_extraction.d.ts.map +1 -0
- package/cjs/api/text_extraction.js +494 -0
- package/cjs/api/text_extraction.js.map +1 -0
- package/cjs/core/index.d.ts +1 -0
- package/cjs/core/index.d.ts.map +1 -1
- package/cjs/core/index.js +2 -0
- package/cjs/core/index.js.map +1 -1
- package/cjs/core/operators/PDFOperator.d.ts +4 -0
- package/cjs/core/operators/PDFOperator.d.ts.map +1 -1
- package/cjs/core/operators/PDFOperator.js +8 -0
- package/cjs/core/operators/PDFOperator.js.map +1 -1
- package/cjs/core/parser/PDFContentStreamParser.d.ts +29 -0
- package/cjs/core/parser/PDFContentStreamParser.d.ts.map +1 -0
- package/cjs/core/parser/PDFContentStreamParser.js +97 -0
- package/cjs/core/parser/PDFContentStreamParser.js.map +1 -0
- package/cjs/core/structures/PDFContentStream.d.ts +2 -0
- package/cjs/core/structures/PDFContentStream.d.ts.map +1 -1
- package/cjs/core/structures/PDFContentStream.js +4 -0
- package/cjs/core/structures/PDFContentStream.js.map +1 -1
- package/cjs/core/structures/PDFPageLeaf.d.ts +2 -0
- package/cjs/core/structures/PDFPageLeaf.d.ts.map +1 -1
- package/cjs/core/structures/PDFPageLeaf.js +4 -0
- package/cjs/core/structures/PDFPageLeaf.js.map +1 -1
- package/cjs/utils/arrays.d.ts +1 -1
- package/dist/pdf-lib.esm.js +595 -1
- package/dist/pdf-lib.esm.js.map +1 -1
- package/dist/pdf-lib.esm.min.js +1 -1
- package/dist/pdf-lib.esm.min.js.map +1 -1
- package/dist/pdf-lib.js +598 -0
- package/dist/pdf-lib.js.map +1 -1
- package/dist/pdf-lib.min.js +1 -1
- package/dist/pdf-lib.min.js.map +1 -1
- package/docs/MIGRATION.md +80 -0
- package/docs/TEXT_EXTRACTION.md +102 -0
- package/es/api/PDFPage.d.ts +12 -0
- package/es/api/PDFPage.d.ts.map +1 -1
- package/es/api/PDFPage.js +18 -0
- package/es/api/PDFPage.js.map +1 -1
- package/es/api/index.d.ts +1 -0
- package/es/api/index.d.ts.map +1 -1
- package/es/api/index.js +1 -0
- package/es/api/index.js.map +1 -1
- package/es/api/text_extraction.d.ts +20 -0
- package/es/api/text_extraction.d.ts.map +1 -0
- package/es/api/text_extraction.js +490 -0
- package/es/api/text_extraction.js.map +1 -0
- package/es/core/index.d.ts +1 -0
- package/es/core/index.d.ts.map +1 -1
- package/es/core/index.js +1 -0
- package/es/core/index.js.map +1 -1
- package/es/core/operators/PDFOperator.d.ts +4 -0
- package/es/core/operators/PDFOperator.d.ts.map +1 -1
- package/es/core/operators/PDFOperator.js +8 -0
- package/es/core/operators/PDFOperator.js.map +1 -1
- package/es/core/parser/PDFContentStreamParser.d.ts +29 -0
- package/es/core/parser/PDFContentStreamParser.d.ts.map +1 -0
- package/es/core/parser/PDFContentStreamParser.js +95 -0
- package/es/core/parser/PDFContentStreamParser.js.map +1 -0
- package/es/core/structures/PDFContentStream.d.ts +2 -0
- package/es/core/structures/PDFContentStream.d.ts.map +1 -1
- package/es/core/structures/PDFContentStream.js +4 -0
- package/es/core/structures/PDFContentStream.js.map +1 -1
- package/es/core/structures/PDFPageLeaf.d.ts +2 -0
- package/es/core/structures/PDFPageLeaf.d.ts.map +1 -1
- package/es/core/structures/PDFPageLeaf.js +4 -0
- package/es/core/structures/PDFPageLeaf.js.map +1 -1
- package/package.json +2 -1
- package/src/api/PDFPage.ts +20 -0
- package/src/api/index.ts +1 -0
- package/src/api/text_extraction.ts +511 -0
- package/src/core/index.ts +1 -0
- package/src/core/operators/PDFOperator.ts +10 -0
- package/src/core/parser/PDFContentStreamParser.ts +106 -0
- package/src/core/structures/PDFContentStream.ts +5 -0
- package/src/core/structures/PDFPageLeaf.ts +5 -0
- package/ts3.4/cjs/api/PDFPage.d.ts +12 -0
- package/ts3.4/cjs/api/index.d.ts +1 -0
- package/ts3.4/cjs/api/rotations.d.ts +1 -1
- package/ts3.4/cjs/api/text_extraction.d.ts +20 -0
- package/ts3.4/cjs/core/index.d.ts +1 -0
- package/ts3.4/cjs/core/operators/PDFOperator.d.ts +4 -0
- package/ts3.4/cjs/core/parser/PDFContentStreamParser.d.ts +29 -0
- package/ts3.4/cjs/core/structures/PDFContentStream.d.ts +2 -0
- package/ts3.4/cjs/core/structures/PDFPageLeaf.d.ts +2 -0
- package/ts3.4/cjs/utils/arrays.d.ts +1 -1
- package/ts3.4/es/api/PDFPage.d.ts +12 -0
- package/ts3.4/es/api/index.d.ts +1 -0
- package/ts3.4/es/api/text_extraction.d.ts +20 -0
- package/ts3.4/es/core/index.d.ts +1 -0
- package/ts3.4/es/core/operators/PDFOperator.d.ts +4 -0
- package/ts3.4/es/core/parser/PDFContentStreamParser.d.ts +29 -0
- package/ts3.4/es/core/structures/PDFContentStream.d.ts +2 -0
- package/ts3.4/es/core/structures/PDFPageLeaf.d.ts +2 -0
package/dist/pdf-lib.esm.js
CHANGED
|
@@ -9292,6 +9292,14 @@ var PDFOperator = /** @class */ (function () {
|
|
|
9292
9292
|
this.name = name;
|
|
9293
9293
|
this.args = args || [];
|
|
9294
9294
|
}
|
|
9295
|
+
/** 只读访问算子名(如 'Tj' / 'TJ'),供内容流解释与文本提取使用。 */
|
|
9296
|
+
PDFOperator.prototype.getName = function () {
|
|
9297
|
+
return this.name;
|
|
9298
|
+
};
|
|
9299
|
+
/** 只读访问算子操作数(返回副本,防止外部改写内部状态)。 */
|
|
9300
|
+
PDFOperator.prototype.getArgs = function () {
|
|
9301
|
+
return this.args.slice();
|
|
9302
|
+
};
|
|
9295
9303
|
PDFOperator.prototype.clone = function (context) {
|
|
9296
9304
|
var args = new Array(this.args.length);
|
|
9297
9305
|
for (var idx = 0, len = args.length; idx < len; idx++) {
|
|
@@ -9476,6 +9484,10 @@ var PDFContentStream = /** @class */ (function (_super) {
|
|
|
9476
9484
|
var _a = this, dict = _a.dict, encode = _a.encode;
|
|
9477
9485
|
return PDFContentStream.of(dict.clone(context), operators, encode);
|
|
9478
9486
|
};
|
|
9487
|
+
/** 只读访问解析后的算子序列(供文本提取/内容分析使用,返回副本防改写)。 */
|
|
9488
|
+
PDFContentStream.prototype.getOperators = function () {
|
|
9489
|
+
return this.operators.slice();
|
|
9490
|
+
};
|
|
9479
9491
|
PDFContentStream.prototype.getContentsString = function () {
|
|
9480
9492
|
var value = '';
|
|
9481
9493
|
for (var idx = 0, len = this.operators.length; idx < len; idx++) {
|
|
@@ -9775,6 +9787,10 @@ var PDFPageLeaf = /** @class */ (function (_super) {
|
|
|
9775
9787
|
this.set(PDFName$1.Contents, Contents);
|
|
9776
9788
|
Contents.push(contentStreamRef);
|
|
9777
9789
|
};
|
|
9790
|
+
/** 用单个内容流整体替换本页 Contents(供文本编辑/内容流重写使用)。 */
|
|
9791
|
+
PDFPageLeaf.prototype.setContentStream = function (contentStreamRef) {
|
|
9792
|
+
this.set(PDFName$1.Contents, contentStreamRef);
|
|
9793
|
+
};
|
|
9778
9794
|
PDFPageLeaf.prototype.wrapContentStreams = function (startStream, endStream) {
|
|
9779
9795
|
var Contents = this.Contents();
|
|
9780
9796
|
if (Contents instanceof PDFArray$1) {
|
|
@@ -16305,6 +16321,91 @@ var PDFObjectParser = /** @class */ (function (_super) {
|
|
|
16305
16321
|
}(BaseParser$1));
|
|
16306
16322
|
var PDFObjectParser$1 = PDFObjectParser;
|
|
16307
16323
|
|
|
16324
|
+
/**
|
|
16325
|
+
* PDF 内容流(Content Stream)解析器。
|
|
16326
|
+
*
|
|
16327
|
+
* 上游 pdf-lib 1.x 只能解析「本库自己在内存里 push 的 PDFOperator」,
|
|
16328
|
+
* 对从外部 PDF 加载进来的内容流(PDFRawStream 里的 Flate 压缩字节)没有
|
|
16329
|
+
* 公开解析入口——这正是它无法实现文本提取的根因。本解析器补上这一能力:
|
|
16330
|
+
* 把解码后的内容流字节还原成 PDFOperator[],供文本提取/内容分析复用。
|
|
16331
|
+
*
|
|
16332
|
+
* 内容流语法 = 若干「操作数 + 关键字」,关键字即算子名(Tj/TJ/BT/...)。
|
|
16333
|
+
* 操作数对象(数字/字符串/十六进制串/名字/数组/字典)复用 PDFObjectParser
|
|
16334
|
+
* 的对象解析,保证与本库其它解析器行为一致。
|
|
16335
|
+
*/
|
|
16336
|
+
var PDFContentStreamParser = /** @class */ (function (_super) {
|
|
16337
|
+
__extends(PDFContentStreamParser, _super);
|
|
16338
|
+
function PDFContentStreamParser(byteStream, context) {
|
|
16339
|
+
var _this = _super.call(this, byteStream) || this;
|
|
16340
|
+
_this.objectParser = PDFObjectParser$1.forByteStream(byteStream, context);
|
|
16341
|
+
return _this;
|
|
16342
|
+
}
|
|
16343
|
+
/** 解析整个内容流为算子序列。遇到无法识别的 token 跳过而非抛错(容错:真实世界 PDF 很脏)。 */
|
|
16344
|
+
PDFContentStreamParser.prototype.parseOperators = function () {
|
|
16345
|
+
var operators = [];
|
|
16346
|
+
var args = [];
|
|
16347
|
+
while (!this.bytes.done()) {
|
|
16348
|
+
this.skipWhitespaceAndComments();
|
|
16349
|
+
if (this.bytes.done())
|
|
16350
|
+
break;
|
|
16351
|
+
var byte = this.bytes.peek();
|
|
16352
|
+
// 对象型操作数:数字、字符串、十六进制串、名字、数组。
|
|
16353
|
+
if (IsNumeric[byte] ||
|
|
16354
|
+
byte === CharCodes$1.LeftParen ||
|
|
16355
|
+
byte === CharCodes$1.LessThan ||
|
|
16356
|
+
byte === CharCodes$1.ForwardSlash ||
|
|
16357
|
+
byte === CharCodes$1.LeftSquareBracket) {
|
|
16358
|
+
try {
|
|
16359
|
+
var obj = this.objectParser.parseObject();
|
|
16360
|
+
args.push(obj);
|
|
16361
|
+
continue;
|
|
16362
|
+
}
|
|
16363
|
+
catch (_a) {
|
|
16364
|
+
// 解析失败的坏 token:吞掉一个字节继续,避免死循环。
|
|
16365
|
+
this.bytes.next();
|
|
16366
|
+
continue;
|
|
16367
|
+
}
|
|
16368
|
+
}
|
|
16369
|
+
// 其余按关键字(算子名)处理:读到分隔符/空白为止。
|
|
16370
|
+
var keyword = this.parseKeyword();
|
|
16371
|
+
if (!keyword) {
|
|
16372
|
+
this.bytes.next();
|
|
16373
|
+
continue;
|
|
16374
|
+
}
|
|
16375
|
+
// 布尔/空值在内容流里极少作为操作数出现,但 PDFObjectParser 能解析,
|
|
16376
|
+
// 这里若遇到也当操作数(提升兼容性)。
|
|
16377
|
+
if (keyword === 'true' || keyword === 'false' || keyword === 'null') {
|
|
16378
|
+
// 回退到关键字起点不可行,这里直接丢弃(内容流里几乎不用布尔作算子)。
|
|
16379
|
+
continue;
|
|
16380
|
+
}
|
|
16381
|
+
// 必须传副本:下面 args.length = 0 会清空同一数组引用,
|
|
16382
|
+
// 若直接传引用,所有算子的操作数都会被抹成空(真跑单测抓到)。
|
|
16383
|
+
operators.push(PDFOperator$1.of(keyword, args.slice()));
|
|
16384
|
+
args.length = 0;
|
|
16385
|
+
}
|
|
16386
|
+
return operators;
|
|
16387
|
+
};
|
|
16388
|
+
/** 读取一个关键字 token(字母/符号组成,非空白非分隔符)。 */
|
|
16389
|
+
PDFContentStreamParser.prototype.parseKeyword = function () {
|
|
16390
|
+
var value = '';
|
|
16391
|
+
while (!this.bytes.done()) {
|
|
16392
|
+
var byte = this.bytes.peek();
|
|
16393
|
+
if (IsWhitespace[byte] || IsDelimiter[byte])
|
|
16394
|
+
break;
|
|
16395
|
+
value += charFromCode(this.bytes.next());
|
|
16396
|
+
}
|
|
16397
|
+
return value;
|
|
16398
|
+
};
|
|
16399
|
+
PDFContentStreamParser.forBytes = function (bytes, context) {
|
|
16400
|
+
return new PDFContentStreamParser(ByteStream$1.of(bytes), context);
|
|
16401
|
+
};
|
|
16402
|
+
PDFContentStreamParser.fromPDFRawStream = function (stream, context) {
|
|
16403
|
+
return new PDFContentStreamParser(ByteStream$1.fromPDFRawStream(stream), context);
|
|
16404
|
+
};
|
|
16405
|
+
return PDFContentStreamParser;
|
|
16406
|
+
}(BaseParser$1));
|
|
16407
|
+
var PDFContentStreamParser$1 = PDFContentStreamParser;
|
|
16408
|
+
|
|
16308
16409
|
var PDFObjectStreamParser = /** @class */ (function (_super) {
|
|
16309
16410
|
__extends(PDFObjectStreamParser, _super);
|
|
16310
16411
|
function PDFObjectStreamParser(rawStream, shouldWaitForTick) {
|
|
@@ -25029,6 +25130,24 @@ var PDFPage = /** @class */ (function () {
|
|
|
25029
25130
|
* ```
|
|
25030
25131
|
* @returns The default position of the page.
|
|
25031
25132
|
*/
|
|
25133
|
+
/**
|
|
25134
|
+
* 提取本页的可搜索文本(尽力而为的文本还原)。
|
|
25135
|
+
*
|
|
25136
|
+
* 解释内容流里的文本显示算子(Tj/TJ/'/"),按字体编码还原为 Unicode,
|
|
25137
|
+
* 并按文本定位算子插入换行。支持标准 14 字体与带 ToUnicode 的嵌入字体;
|
|
25138
|
+
* 对无 ToUnicode 的 CID 字体/旋转文本等复杂情形不保证逐字一致。
|
|
25139
|
+
*
|
|
25140
|
+
* @returns 按绘制顺序排列的文本行数组(空页返回空数组)。
|
|
25141
|
+
*/
|
|
25142
|
+
PDFPage.prototype.extractTextLines = function () {
|
|
25143
|
+
// 延迟引入,避免与 PDFPage 形成循环依赖的顶层初始化问题。
|
|
25144
|
+
var extractTextFromPage = require("./text_extraction").extractTextFromPage;
|
|
25145
|
+
return extractTextFromPage(this);
|
|
25146
|
+
};
|
|
25147
|
+
/** 提取本页文本,行间以 `\n` 连接(extractTextLines 的字符串便捷版)。 */
|
|
25148
|
+
PDFPage.prototype.extractText = function () {
|
|
25149
|
+
return this.extractTextLines().join('\n');
|
|
25150
|
+
};
|
|
25032
25151
|
PDFPage.prototype.getPosition = function () {
|
|
25033
25152
|
return { x: this.x, y: this.y };
|
|
25034
25153
|
};
|
|
@@ -26035,5 +26154,480 @@ var PDFButton = /** @class */ (function (_super) {
|
|
|
26035
26154
|
}(PDFField$1));
|
|
26036
26155
|
var PDFButton$1 = PDFButton;
|
|
26037
26156
|
|
|
26038
|
-
|
|
26157
|
+
/** 为某一种标准字体编码建立 byte → 字符 的反查表。 */
|
|
26158
|
+
var buildStandardDecoder = function (encoding) {
|
|
26159
|
+
var table = new Array(256).fill('');
|
|
26160
|
+
for (var _i = 0, _a = encoding.supportedCodePoints; _i < _a.length; _i++) {
|
|
26161
|
+
var cp = _a[_i];
|
|
26162
|
+
try {
|
|
26163
|
+
var code = encoding.encodeUnicodeCodePoint(cp).code;
|
|
26164
|
+
if (code >= 0 && code < 256 && !table[code]) {
|
|
26165
|
+
table[code] = String.fromCodePoint(cp);
|
|
26166
|
+
}
|
|
26167
|
+
}
|
|
26168
|
+
catch (_b) {
|
|
26169
|
+
/* 不可编码的码点跳过 */
|
|
26170
|
+
}
|
|
26171
|
+
}
|
|
26172
|
+
return function (bytes) {
|
|
26173
|
+
var _a;
|
|
26174
|
+
var out = '';
|
|
26175
|
+
for (var i = 0; i < bytes.length; i++)
|
|
26176
|
+
out += (_a = table[bytes[i]]) !== null && _a !== void 0 ? _a : '';
|
|
26177
|
+
return out;
|
|
26178
|
+
};
|
|
26179
|
+
};
|
|
26180
|
+
var winAnsiDecoder = buildStandardDecoder(Encodings.WinAnsi);
|
|
26181
|
+
var symbolDecoder = buildStandardDecoder(Encodings.Symbol);
|
|
26182
|
+
var zapfDecoder = buildStandardDecoder(Encodings.ZapfDingbats);
|
|
26183
|
+
/** 根据字体字典的 BaseFont 名选择一个解码器。 */
|
|
26184
|
+
var decoderForBaseFont = function (baseFont) {
|
|
26185
|
+
var name = baseFont.replace(/^.*[+]/, ''); // 去掉 subset 前缀 "ABCDEF+"
|
|
26186
|
+
if (name === 'Symbol')
|
|
26187
|
+
return symbolDecoder;
|
|
26188
|
+
if (name === 'ZapfDingbats')
|
|
26189
|
+
return zapfDecoder;
|
|
26190
|
+
if (name.includes('Courier') ||
|
|
26191
|
+
name.includes('Helvetica') ||
|
|
26192
|
+
name.includes('Times')) {
|
|
26193
|
+
return winAnsiDecoder;
|
|
26194
|
+
}
|
|
26195
|
+
// 其它(嵌入字体且无 ToUnicode):回退 PDFDocEncoding
|
|
26196
|
+
return function (bytes) { return pdfDocEncodingDecode(bytes); };
|
|
26197
|
+
};
|
|
26198
|
+
/** 解析 ToUnicode CMap 的 codespace/bfchar/bfrange,构建 code → string 映射。 */
|
|
26199
|
+
var decodeToUnicode = function (cmapBytes) {
|
|
26200
|
+
var text = new TextDecoder('latin1').decode(cmapBytes);
|
|
26201
|
+
var map = new Map();
|
|
26202
|
+
var spaces = [];
|
|
26203
|
+
var maxCodeBytes = 1;
|
|
26204
|
+
/** 去掉尖括号与空白,保留原始 hex 位数(用于判断 1/2/4 字节 code)。 */
|
|
26205
|
+
var parseHex = function (s) {
|
|
26206
|
+
return s.trim().replace(/^<|>$/g, '').replace(/\s+/g, '');
|
|
26207
|
+
};
|
|
26208
|
+
var hexToCode = function (h) { return parseInt(h, 16); };
|
|
26209
|
+
var codeKey = function (hex, code) {
|
|
26210
|
+
return Math.ceil(hex.length / 2) + ":" + code;
|
|
26211
|
+
};
|
|
26212
|
+
var hexToUnicode = function (h) {
|
|
26213
|
+
var clean = h.replace(/\s+/g, '');
|
|
26214
|
+
if (clean.length <= 4)
|
|
26215
|
+
return String.fromCodePoint(parseInt(clean, 16));
|
|
26216
|
+
// ToUnicode 目标通常是 UTF-16BE 单元序列(4 位一组);超过 BMP 时按码点处理。
|
|
26217
|
+
if (clean.length % 4 === 0) {
|
|
26218
|
+
var out = '';
|
|
26219
|
+
for (var i = 0; i + 4 <= clean.length; i += 4) {
|
|
26220
|
+
out += String.fromCharCode(parseInt(clean.slice(i, i + 4), 16));
|
|
26221
|
+
}
|
|
26222
|
+
return out;
|
|
26223
|
+
}
|
|
26224
|
+
return String.fromCodePoint(parseInt(clean, 16));
|
|
26225
|
+
};
|
|
26226
|
+
var addCodeSpace = function (loHex, hiHex) {
|
|
26227
|
+
var bytes = Math.ceil(loHex.length / 2);
|
|
26228
|
+
var entry = { bytes: bytes, lo: hexToCode(loHex), hi: hexToCode(hiHex) };
|
|
26229
|
+
spaces.push(entry);
|
|
26230
|
+
if (bytes > maxCodeBytes)
|
|
26231
|
+
maxCodeBytes = bytes;
|
|
26232
|
+
};
|
|
26233
|
+
// codespace 决定一个 code 占几个字节。CJK 嵌入字体常见 <0000><ffff>,
|
|
26234
|
+
// 必须按 2 字节读,逐字节解会把每个汉字拆成两个错误字符(实测踩到)。
|
|
26235
|
+
var spaceRe = /begincodespacerange([\s\S]*?)endcodespacerange/g;
|
|
26236
|
+
var m;
|
|
26237
|
+
m = spaceRe.exec(text);
|
|
26238
|
+
while (m) {
|
|
26239
|
+
for (var _i = 0, _a = m[1].trim().split(/\r?\n/); _i < _a.length; _i++) {
|
|
26240
|
+
var line = _a[_i];
|
|
26241
|
+
// fontkit 生成的是 `<0000><ffff>`(中间无空格),必须按尖括号取 token,
|
|
26242
|
+
// 不能用 whitespace split,否则会把两个 hex 粘成一个无效值。
|
|
26243
|
+
var tokens = line.match(/<[^>]*>/g);
|
|
26244
|
+
if (tokens && tokens.length >= 2) {
|
|
26245
|
+
addCodeSpace(parseHex(tokens[0]), parseHex(tokens[1]));
|
|
26246
|
+
}
|
|
26247
|
+
}
|
|
26248
|
+
m = spaceRe.exec(text);
|
|
26249
|
+
}
|
|
26250
|
+
// beginbfchar ... endbfchar
|
|
26251
|
+
var bfcharRe = /beginbfchar([\s\S]*?)endbfchar/g;
|
|
26252
|
+
m = bfcharRe.exec(text);
|
|
26253
|
+
while (m) {
|
|
26254
|
+
for (var _b = 0, _c = m[1].trim().split(/\r?\n/); _b < _c.length; _b++) {
|
|
26255
|
+
var line = _c[_b];
|
|
26256
|
+
var parts = line.trim().split(/\s+/);
|
|
26257
|
+
if (parts.length < 2)
|
|
26258
|
+
continue;
|
|
26259
|
+
var srcHex = parseHex(parts[0]);
|
|
26260
|
+
map.set(codeKey(srcHex, hexToCode(srcHex)), hexToUnicode(parseHex(parts[1])));
|
|
26261
|
+
}
|
|
26262
|
+
m = bfcharRe.exec(text);
|
|
26263
|
+
}
|
|
26264
|
+
// beginbfrange ... endbfrange
|
|
26265
|
+
var bfrangeRe = /beginbfrange([\s\S]*?)endbfrange/g;
|
|
26266
|
+
m = bfrangeRe.exec(text);
|
|
26267
|
+
while (m) {
|
|
26268
|
+
for (var _d = 0, _e = m[1].trim().split(/\r?\n/); _d < _e.length; _d++) {
|
|
26269
|
+
var line = _e[_d];
|
|
26270
|
+
var parts = line.trim().split(/\s+/);
|
|
26271
|
+
if (parts.length < 3)
|
|
26272
|
+
continue;
|
|
26273
|
+
var loHex = parseHex(parts[0]);
|
|
26274
|
+
var hiHex = parseHex(parts[1]);
|
|
26275
|
+
var lo = hexToCode(loHex);
|
|
26276
|
+
var hi = hexToCode(hiHex);
|
|
26277
|
+
var bytes = Math.ceil(loHex.length / 2);
|
|
26278
|
+
var targetTokens = parts
|
|
26279
|
+
.slice(2)
|
|
26280
|
+
.join(' ')
|
|
26281
|
+
.match(/<[^>]*>/g);
|
|
26282
|
+
if (targetTokens && targetTokens.length === hi - lo + 1) {
|
|
26283
|
+
for (var c = lo; c <= hi; c++) {
|
|
26284
|
+
map.set(bytes + ":" + c, hexToUnicode(parseHex(targetTokens[c - lo])));
|
|
26285
|
+
}
|
|
26286
|
+
}
|
|
26287
|
+
else {
|
|
26288
|
+
var dstHex = parseHex(parts[2]);
|
|
26289
|
+
var base = hexToCode(dstHex);
|
|
26290
|
+
for (var c = lo; c <= hi; c++) {
|
|
26291
|
+
var target = (base + (c - lo))
|
|
26292
|
+
.toString(16)
|
|
26293
|
+
.padStart(dstHex.length, '0');
|
|
26294
|
+
map.set(bytes + ":" + c, hexToUnicode(target));
|
|
26295
|
+
}
|
|
26296
|
+
}
|
|
26297
|
+
}
|
|
26298
|
+
m = bfrangeRe.exec(text);
|
|
26299
|
+
}
|
|
26300
|
+
return function (bytes) {
|
|
26301
|
+
var _a, _b;
|
|
26302
|
+
var out = '';
|
|
26303
|
+
var i = 0;
|
|
26304
|
+
while (i < bytes.length) {
|
|
26305
|
+
var matched = false;
|
|
26306
|
+
var _loop_1 = function (len) {
|
|
26307
|
+
if (i + len > bytes.length)
|
|
26308
|
+
return "continue";
|
|
26309
|
+
var code = 0;
|
|
26310
|
+
for (var j = 0; j < len; j++)
|
|
26311
|
+
code = (code << 8) | bytes[i + j];
|
|
26312
|
+
var inSpace = spaces.some(function (s) { return s.bytes === len && code >= s.lo && code <= s.hi; });
|
|
26313
|
+
if (!inSpace)
|
|
26314
|
+
return "continue";
|
|
26315
|
+
out += (_a = map.get(len + ":" + code)) !== null && _a !== void 0 ? _a : '';
|
|
26316
|
+
i += len;
|
|
26317
|
+
matched = true;
|
|
26318
|
+
return "break";
|
|
26319
|
+
};
|
|
26320
|
+
// 优先最长的合法 codespace(2 字节域不会误吞 1 字节域)。
|
|
26321
|
+
for (var len = maxCodeBytes; len >= 1; len--) {
|
|
26322
|
+
var state_1 = _loop_1(len);
|
|
26323
|
+
if (state_1 === "break")
|
|
26324
|
+
break;
|
|
26325
|
+
}
|
|
26326
|
+
if (!matched) {
|
|
26327
|
+
// codespace 缺失或写错时,退化为单字节,至少不吞掉后续内容。
|
|
26328
|
+
out += (_b = map.get("1:" + bytes[i])) !== null && _b !== void 0 ? _b : '';
|
|
26329
|
+
i += 1;
|
|
26330
|
+
}
|
|
26331
|
+
}
|
|
26332
|
+
return out;
|
|
26333
|
+
};
|
|
26334
|
+
};
|
|
26335
|
+
/** 把显示文本的参数(PDFString/PDFHexString/PDFArray)解码成字符串。 */
|
|
26336
|
+
var decodeShowArg = function (arg, state) {
|
|
26337
|
+
if (arg instanceof PDFHexString$1 || arg instanceof PDFString$1) {
|
|
26338
|
+
return state.decoder(arg.asBytes());
|
|
26339
|
+
}
|
|
26340
|
+
if (arg instanceof PDFArray$1) {
|
|
26341
|
+
// TJ:数组中字符串显示、数字调整字距(负数表示拉开,正数收紧)。
|
|
26342
|
+
var out = '';
|
|
26343
|
+
for (var i = 0; i < arg.size(); i++) {
|
|
26344
|
+
var el = arg.get(i);
|
|
26345
|
+
if (el instanceof PDFHexString$1 || el instanceof PDFString$1) {
|
|
26346
|
+
out += state.decoder(el.asBytes());
|
|
26347
|
+
}
|
|
26348
|
+
else if (el instanceof PDFNumber$1) {
|
|
26349
|
+
// 只在字距调整很大时插入空格,模拟词间停顿(启发式,不精确)。
|
|
26350
|
+
if (el.asNumber() < -180)
|
|
26351
|
+
out += ' ';
|
|
26352
|
+
}
|
|
26353
|
+
}
|
|
26354
|
+
return out;
|
|
26355
|
+
}
|
|
26356
|
+
return '';
|
|
26357
|
+
};
|
|
26358
|
+
var flushLine = function (state) {
|
|
26359
|
+
if (state.line.length) {
|
|
26360
|
+
state.lines.push(state.line.replace(/\s+$/, ''));
|
|
26361
|
+
state.line = '';
|
|
26362
|
+
}
|
|
26363
|
+
};
|
|
26364
|
+
/** 解释一组算子,做文本提取。 */
|
|
26365
|
+
var interpret = function (operators, fonts) {
|
|
26366
|
+
var _a;
|
|
26367
|
+
var state = {
|
|
26368
|
+
line: '',
|
|
26369
|
+
lines: [],
|
|
26370
|
+
decoder: winAnsiDecoder,
|
|
26371
|
+
};
|
|
26372
|
+
for (var _i = 0, operators_1 = operators; _i < operators_1.length; _i++) {
|
|
26373
|
+
var op = operators_1[_i];
|
|
26374
|
+
var name_1 = op.getName();
|
|
26375
|
+
var args = op.getArgs();
|
|
26376
|
+
switch (name_1) {
|
|
26377
|
+
case 'Tf': {
|
|
26378
|
+
var fontName = args[0] instanceof PDFName$1 ? args[0].asString() : '';
|
|
26379
|
+
state.decoder = (_a = fonts.get(fontName)) !== null && _a !== void 0 ? _a : winAnsiDecoder;
|
|
26380
|
+
break;
|
|
26381
|
+
}
|
|
26382
|
+
case 'Tj':
|
|
26383
|
+
state.line += decodeShowArg(args[0], state);
|
|
26384
|
+
break;
|
|
26385
|
+
case 'TJ':
|
|
26386
|
+
state.line += decodeShowArg(args[0], state);
|
|
26387
|
+
break;
|
|
26388
|
+
case '\'': // 换行并显示
|
|
26389
|
+
flushLine(state);
|
|
26390
|
+
if (args[0])
|
|
26391
|
+
state.line += decodeShowArg(args[0], state);
|
|
26392
|
+
break;
|
|
26393
|
+
case '"': // 设置字距/词距 + 换行 + 显示
|
|
26394
|
+
flushLine(state);
|
|
26395
|
+
if (args[2])
|
|
26396
|
+
state.line += decodeShowArg(args[2], state);
|
|
26397
|
+
break;
|
|
26398
|
+
case 'Td':
|
|
26399
|
+
case 'TD': {
|
|
26400
|
+
// 只有纵向移动(第二个操作数非 0)才换行;同一行内的横向移动不换行。
|
|
26401
|
+
var y = args[1] instanceof PDFNumber$1 ? args[1].asNumber() : 0;
|
|
26402
|
+
if (y !== 0)
|
|
26403
|
+
flushLine(state);
|
|
26404
|
+
break;
|
|
26405
|
+
}
|
|
26406
|
+
case 'T*':
|
|
26407
|
+
flushLine(state);
|
|
26408
|
+
break;
|
|
26409
|
+
case 'Tm': {
|
|
26410
|
+
// 文本矩阵:y 分量(索引 5)变化视为换行。
|
|
26411
|
+
var y = args[5] instanceof PDFNumber$1 ? args[5].asNumber() : 0;
|
|
26412
|
+
if (state.line &&
|
|
26413
|
+
state._lastTmY !== undefined &&
|
|
26414
|
+
state._lastTmY !== y) {
|
|
26415
|
+
flushLine(state);
|
|
26416
|
+
}
|
|
26417
|
+
state._lastTmY = y;
|
|
26418
|
+
break;
|
|
26419
|
+
}
|
|
26420
|
+
case 'ET':
|
|
26421
|
+
flushLine(state);
|
|
26422
|
+
break;
|
|
26423
|
+
}
|
|
26424
|
+
}
|
|
26425
|
+
flushLine(state);
|
|
26426
|
+
return state.lines;
|
|
26427
|
+
};
|
|
26428
|
+
/**
|
|
26429
|
+
* 内存文档里字体字典是懒嵌入的:embedFont 只分配 ref,真正 context.assign 发生在 save。
|
|
26430
|
+
* 所以 save 前 context.lookup(ref) 为空;此时直接从 PDFFont 内部的 embedder/fontkit 对象
|
|
26431
|
+
* 重建 glyphId → Unicode 映射,避免把 CJK 子集 CID 当 WinAnsi 解成乱码。
|
|
26432
|
+
*/
|
|
26433
|
+
var decoderFromEmbeddedFont = function (pdfFont) {
|
|
26434
|
+
var embedder = pdfFont && pdfFont.embedder;
|
|
26435
|
+
if (!embedder)
|
|
26436
|
+
return undefined;
|
|
26437
|
+
var font = embedder.font;
|
|
26438
|
+
if (!font || !font.characterSet || !font.glyphForCodePoint)
|
|
26439
|
+
return undefined;
|
|
26440
|
+
var glyphToUnicode = new Map();
|
|
26441
|
+
for (var _i = 0, _a = font.characterSet; _i < _a.length; _i++) {
|
|
26442
|
+
var cp = _a[_i];
|
|
26443
|
+
var glyph = font.glyphForCodePoint(cp);
|
|
26444
|
+
if (!glyph)
|
|
26445
|
+
continue;
|
|
26446
|
+
var id = typeof embedder.glyphId === 'function'
|
|
26447
|
+
? embedder.glyphId(glyph)
|
|
26448
|
+
: glyph.id;
|
|
26449
|
+
if (typeof id === 'number' && id >= 0 && !glyphToUnicode.has(id)) {
|
|
26450
|
+
glyphToUnicode.set(id, String.fromCodePoint(cp));
|
|
26451
|
+
}
|
|
26452
|
+
}
|
|
26453
|
+
if (glyphToUnicode.size === 0)
|
|
26454
|
+
return undefined;
|
|
26455
|
+
return function (bytes) {
|
|
26456
|
+
var _a;
|
|
26457
|
+
var out = '';
|
|
26458
|
+
// Identity-H 编码:每个 glyph id 固定 2 字节。
|
|
26459
|
+
for (var i = 0; i + 1 < bytes.length; i += 2) {
|
|
26460
|
+
var code = (bytes[i] << 8) | bytes[i + 1];
|
|
26461
|
+
out += (_a = glyphToUnicode.get(code)) !== null && _a !== void 0 ? _a : '';
|
|
26462
|
+
}
|
|
26463
|
+
return out;
|
|
26464
|
+
};
|
|
26465
|
+
};
|
|
26466
|
+
/** 从页面 Resources.Font 构建 fontName → Decoder 映射。 */
|
|
26467
|
+
var buildFontDecoders = function (page) {
|
|
26468
|
+
var map = new Map();
|
|
26469
|
+
var context = page.doc.context;
|
|
26470
|
+
var resources = page.node.Resources();
|
|
26471
|
+
if (!resources)
|
|
26472
|
+
return map;
|
|
26473
|
+
var fontsDict = resources.lookupMaybe(PDFName$1.of('Font'), PDFDict$1);
|
|
26474
|
+
if (!fontsDict)
|
|
26475
|
+
return map;
|
|
26476
|
+
var _loop_2 = function (nameObj, refObj) {
|
|
26477
|
+
var fontName = nameObj.asString();
|
|
26478
|
+
var fontDict = void 0;
|
|
26479
|
+
if (refObj instanceof PDFDict$1) {
|
|
26480
|
+
fontDict = refObj;
|
|
26481
|
+
}
|
|
26482
|
+
else if (refObj instanceof PDFRef$1) {
|
|
26483
|
+
fontDict = context.lookupMaybe(refObj, PDFDict$1);
|
|
26484
|
+
}
|
|
26485
|
+
if (!fontDict) {
|
|
26486
|
+
// save 前的内存字体:从 PDFFont 内部的 fontkit 对象重建解码表。
|
|
26487
|
+
if (refObj instanceof PDFRef$1) {
|
|
26488
|
+
var internalFonts = page.doc.fonts || [];
|
|
26489
|
+
var pdfFont = internalFonts.find(function (f) { return f && f.ref === refObj; });
|
|
26490
|
+
var decoder = decoderFromEmbeddedFont(pdfFont);
|
|
26491
|
+
if (decoder) {
|
|
26492
|
+
map.set(fontName, decoder);
|
|
26493
|
+
return "continue";
|
|
26494
|
+
}
|
|
26495
|
+
}
|
|
26496
|
+
return "continue";
|
|
26497
|
+
}
|
|
26498
|
+
// ToUnicode CMap 优先。
|
|
26499
|
+
// 注意:同 context 里该值可能是 PDFRawStream 本体而非 PDFRef;
|
|
26500
|
+
// 用 lookupMaybe(PDFRef) 会对非 ref 抛 UnexpectedObjectTypeError(CJK 嵌入字体实测抓到)。
|
|
26501
|
+
var toUnicodeRaw = fontDict.get(PDFName$1.of('ToUnicode'));
|
|
26502
|
+
var cmapStream = void 0;
|
|
26503
|
+
if (toUnicodeRaw instanceof PDFStream$1)
|
|
26504
|
+
cmapStream = toUnicodeRaw;
|
|
26505
|
+
else if (toUnicodeRaw instanceof PDFRef$1) {
|
|
26506
|
+
cmapStream = context.lookupMaybe(toUnicodeRaw, PDFStream$1);
|
|
26507
|
+
}
|
|
26508
|
+
if (cmapStream) {
|
|
26509
|
+
try {
|
|
26510
|
+
// ToUnicode 由 context.flateStream(cmap) 写入,Filter=FlateDecode。
|
|
26511
|
+
// 必须先按 PDF 流解码,否则拿到的只是 zlib 压缩字节,CMap 解析必为空。
|
|
26512
|
+
var cmapBytes = decodePDFRawStream(cmapStream).decode();
|
|
26513
|
+
map.set(fontName, decodeToUnicode(cmapBytes));
|
|
26514
|
+
return "continue";
|
|
26515
|
+
}
|
|
26516
|
+
catch (_a) {
|
|
26517
|
+
/* CMap 解析失败,回退到编码推断 */
|
|
26518
|
+
}
|
|
26519
|
+
}
|
|
26520
|
+
var baseFont = fontDict.lookupMaybe(PDFName$1.of('BaseFont'), PDFName$1);
|
|
26521
|
+
map.set(fontName, decoderForBaseFont(baseFont ? baseFont.asString() : ''));
|
|
26522
|
+
};
|
|
26523
|
+
for (var _i = 0, _a = fontsDict.entries(); _i < _a.length; _i++) {
|
|
26524
|
+
var _b = _a[_i], nameObj = _b[0], refObj = _b[1];
|
|
26525
|
+
_loop_2(nameObj, refObj);
|
|
26526
|
+
}
|
|
26527
|
+
return map;
|
|
26528
|
+
};
|
|
26529
|
+
/** 把页 Contents(单流或流数组)解析为算子。 */
|
|
26530
|
+
var pageOperators = function (page) {
|
|
26531
|
+
var contents = page.node.Contents();
|
|
26532
|
+
if (!contents)
|
|
26533
|
+
return [];
|
|
26534
|
+
var context = page.doc.context;
|
|
26535
|
+
var streams = contents instanceof PDFArray$1
|
|
26536
|
+
? Array.from({ length: contents.size() }, function (_, i) { return contents.get(i); })
|
|
26537
|
+
: [contents];
|
|
26538
|
+
var ops = [];
|
|
26539
|
+
for (var _i = 0, streams_1 = streams; _i < streams_1.length; _i++) {
|
|
26540
|
+
var s = streams_1[_i];
|
|
26541
|
+
var stream = s instanceof PDFRef$1
|
|
26542
|
+
? context.lookupMaybe(s, PDFStream$1)
|
|
26543
|
+
: s;
|
|
26544
|
+
if (!stream)
|
|
26545
|
+
continue;
|
|
26546
|
+
if (stream instanceof PDFContentStream$1) {
|
|
26547
|
+
ops.push.apply(ops, stream.getOperators());
|
|
26548
|
+
}
|
|
26549
|
+
else {
|
|
26550
|
+
try {
|
|
26551
|
+
ops.push.apply(ops, PDFContentStreamParser$1.fromPDFRawStream(stream, context).parseOperators());
|
|
26552
|
+
}
|
|
26553
|
+
catch (_a) {
|
|
26554
|
+
/* 单个流解析失败跳过,尽量提取其它流 */
|
|
26555
|
+
}
|
|
26556
|
+
}
|
|
26557
|
+
}
|
|
26558
|
+
return ops;
|
|
26559
|
+
};
|
|
26560
|
+
/** 提取页面文本,按行返回。 */
|
|
26561
|
+
var extractTextFromPage = function (page) {
|
|
26562
|
+
return interpret(pageOperators(page), buildFontDecoders(page));
|
|
26563
|
+
};
|
|
26564
|
+
/** 提取页面文本,合并为单个字符串(行间以 \n 连接)。 */
|
|
26565
|
+
var extractText = function (page) {
|
|
26566
|
+
return extractTextFromPage(page).join('\n');
|
|
26567
|
+
};
|
|
26568
|
+
/**
|
|
26569
|
+
* 删除页面中「解码文本包含给定子串」的文本显示算子(文本删除 / redaction 基础)。
|
|
26570
|
+
*
|
|
26571
|
+
* 行为:解析页面内容流,找到 Tj / TJ / ' / " 算子中解码后含 `substring` 的,
|
|
26572
|
+
* 连同其紧邻的换行算子(T* / ' / " 自带的换行语义)一并移除,其余绘图算子
|
|
26573
|
+
* 原样保留,然后用一个新内容流整体替换本页内容。
|
|
26574
|
+
*
|
|
26575
|
+
* 边界(诚实说明):删除的是「整段显示算子」,不是逐字删除——若一段 Tj 里
|
|
26576
|
+
* 只有部分文字匹配,整段都会被移除。这是内容流模型的固有限制,符合
|
|
26577
|
+
* pdf-lib 一贯的「绘制指令而非文本模型」语义。
|
|
26578
|
+
*
|
|
26579
|
+
* @returns 被删除的显示算子数量(0 表示没有匹配,页面未改动)。
|
|
26580
|
+
*/
|
|
26581
|
+
var removeTextContaining = function (page, substring) {
|
|
26582
|
+
var _a;
|
|
26583
|
+
if (!substring)
|
|
26584
|
+
return 0;
|
|
26585
|
+
var fonts = buildFontDecoders(page);
|
|
26586
|
+
var ops = pageOperators(page);
|
|
26587
|
+
var context = page.doc.context;
|
|
26588
|
+
// 第一遍:标记要删除的算子索引,同时跟踪 Tf 以正确解码后续文本。
|
|
26589
|
+
var removeIdx = new Set();
|
|
26590
|
+
var activeDecoder = winAnsiDecoder;
|
|
26591
|
+
for (var i = 0; i < ops.length; i++) {
|
|
26592
|
+
var op = ops[i];
|
|
26593
|
+
var name_2 = op.getName();
|
|
26594
|
+
var args = op.getArgs();
|
|
26595
|
+
if (name_2 === 'Tf') {
|
|
26596
|
+
var fn = args[0] instanceof PDFName$1 ? args[0].asString() : '';
|
|
26597
|
+
activeDecoder = (_a = fonts.get(fn)) !== null && _a !== void 0 ? _a : winAnsiDecoder;
|
|
26598
|
+
continue;
|
|
26599
|
+
}
|
|
26600
|
+
if (name_2 === 'Tj' || name_2 === 'TJ' || name_2 === '\'' || name_2 === '"') {
|
|
26601
|
+
var arg = void 0;
|
|
26602
|
+
if (name_2 === 'Tj' || name_2 === 'TJ')
|
|
26603
|
+
arg = args[0];
|
|
26604
|
+
else
|
|
26605
|
+
arg = args[args.length - 1];
|
|
26606
|
+
if (arg) {
|
|
26607
|
+
var st = {
|
|
26608
|
+
line: '',
|
|
26609
|
+
lines: [],
|
|
26610
|
+
decoder: activeDecoder,
|
|
26611
|
+
};
|
|
26612
|
+
var text = decodeShowArg(arg, st);
|
|
26613
|
+
if (text.includes(substring))
|
|
26614
|
+
removeIdx.add(i);
|
|
26615
|
+
}
|
|
26616
|
+
}
|
|
26617
|
+
}
|
|
26618
|
+
if (removeIdx.size === 0)
|
|
26619
|
+
return 0;
|
|
26620
|
+
// 第二遍:保留未删除算子,重建内容流。
|
|
26621
|
+
var kept = ops.filter(function (_, i) { return !removeIdx.has(i); });
|
|
26622
|
+
var dict = context.obj({});
|
|
26623
|
+
var newStream = PDFContentStream$1.of(dict, kept);
|
|
26624
|
+
var ref = context.register(newStream);
|
|
26625
|
+
page.node.setContentStream(ref);
|
|
26626
|
+
// 清掉页面缓存的旧内存内容流引用,避免后续 drawText 追加到已废弃的流。
|
|
26627
|
+
page.contentStream = undefined;
|
|
26628
|
+
page.contentStreamRef = ref;
|
|
26629
|
+
return removeIdx.size;
|
|
26630
|
+
};
|
|
26631
|
+
|
|
26632
|
+
export { AFRelationship, AcroButtonFlags, AcroChoiceFlags, AcroFieldFlags, AcroTextFlags, AnnotationFlags, AppearanceCharacteristics$1 as AppearanceCharacteristics, BlendMode, Cache$1 as Cache, CharCodes$1 as CharCodes, ColorTypes, CombedTextLayoutError, CorruptPageTreeError, CustomFontEmbedder$1 as CustomFontEmbedder, CustomFontSubsetEmbedder$1 as CustomFontSubsetEmbedder, Duplex, EncryptedPDFError, ExceededMaxLengthError, FieldAlreadyExistsError, FieldExistsAsNonTerminalError, FileEmbedder$1 as FileEmbedder, FontkitNotRegisteredError, ForeignPageError, ImageAlignment, IndexOutOfBoundsError, InvalidAcroFieldValueError, InvalidFieldNamePartError, InvalidMaxLengthError, InvalidPDFDateStringError, InvalidTargetIndexError, JpegEmbedder$1 as JpegEmbedder, LineCapStyle, LineJoinStyle, MethodNotImplementedError, MissingCatalogError, MissingDAEntryError, MissingKeywordError, MissingOnValueCheckError, MissingPDFHeaderError, MissingPageContentsEmbeddingError, MissingTfOperatorError, MultiSelectValueError, NextByteAssertionError, NoSuchFieldError, NonFullScreenPageMode, NumberParsingError, PDFAcroButton$1 as PDFAcroButton, PDFAcroCheckBox$1 as PDFAcroCheckBox, PDFAcroChoice$1 as PDFAcroChoice, PDFAcroComboBox$1 as PDFAcroComboBox, PDFAcroField$1 as PDFAcroField, PDFAcroForm$1 as PDFAcroForm, PDFAcroListBox$1 as PDFAcroListBox, PDFAcroNonTerminal$1 as PDFAcroNonTerminal, PDFAcroPushButton$1 as PDFAcroPushButton, PDFAcroRadioButton$1 as PDFAcroRadioButton, PDFAcroSignature$1 as PDFAcroSignature, PDFAcroTerminal$1 as PDFAcroTerminal, PDFAcroText$1 as PDFAcroText, PDFAnnotation$1 as PDFAnnotation, PDFArray$1 as PDFArray, PDFArrayIsNotRectangleError, PDFBool$1 as PDFBool, PDFButton$1 as PDFButton, PDFCatalog$1 as PDFCatalog, PDFCheckBox$1 as PDFCheckBox, PDFContentStream$1 as PDFContentStream, PDFContentStreamParser$1 as PDFContentStreamParser, PDFContext$1 as PDFContext, PDFCrossRefSection$1 as PDFCrossRefSection, PDFCrossRefStream$1 as PDFCrossRefStream, PDFDict$1 as PDFDict, PDFDocument$1 as PDFDocument, PDFDropdown$1 as PDFDropdown, PDFEmbeddedPage$1 as PDFEmbeddedPage, PDFField$1 as PDFField, PDFFlateStream$1 as PDFFlateStream, PDFFont$1 as PDFFont, PDFForm$1 as PDFForm, PDFHeader$1 as PDFHeader, PDFHexString$1 as PDFHexString, PDFImage$1 as PDFImage, PDFInvalidObject$1 as PDFInvalidObject, PDFInvalidObjectParsingError, PDFJavaScript$1 as PDFJavaScript, PDFName$1 as PDFName, PDFNull$1 as PDFNull, PDFNumber$1 as PDFNumber, PDFObject$1 as PDFObject, PDFObjectCopier$1 as PDFObjectCopier, PDFObjectParser$1 as PDFObjectParser, PDFObjectParsingError, PDFObjectStream$1 as PDFObjectStream, PDFObjectStreamParser$1 as PDFObjectStreamParser, PDFOperator$1 as PDFOperator, Ops as PDFOperatorNames, PDFOptionList$1 as PDFOptionList, PDFPage$1 as PDFPage, PDFPageEmbedder$1 as PDFPageEmbedder, PDFPageLeaf$1 as PDFPageLeaf, PDFPageTree$1 as PDFPageTree, PDFParser$1 as PDFParser, PDFParsingError, PDFRadioGroup$1 as PDFRadioGroup, PDFRawStream$1 as PDFRawStream, PDFRef$1 as PDFRef, PDFSignature$1 as PDFSignature, PDFStream$1 as PDFStream, PDFStreamParsingError, PDFStreamWriter$1 as PDFStreamWriter, PDFString$1 as PDFString, PDFTextField$1 as PDFTextField, PDFTrailer$1 as PDFTrailer, PDFTrailerDict$1 as PDFTrailerDict, PDFWidgetAnnotation$1 as PDFWidgetAnnotation, PDFWriter$1 as PDFWriter, PDFXRefStreamParser$1 as PDFXRefStreamParser, PageEmbeddingMismatchedContextError, PageSizes, ParseSpeeds, PngEmbedder$1 as PngEmbedder, PrintScaling, PrivateConstructorError, ReadingDirection, RemovePageFromEmptyDocumentError, ReparseError, RichTextFieldReadError, RotationTypes, StalledParserError, StandardFontEmbedder$1 as StandardFontEmbedder, StandardFontValues, StandardFonts, TextAlignment, TextRenderingMode, UnbalancedParenthesisError, UnexpectedFieldTypeError, UnexpectedObjectTypeError, UnrecognizedStreamTypeError, UnsupportedEncodingError, ViewerPreferences$1 as ViewerPreferences, addRandomSuffix, adjustDimsForRotation, appendBezierCurve, appendQuadraticCurve, arrayAsString, asNumber, asPDFName, asPDFNumber, assertEachIs, assertInteger, assertIs, assertIsOneOf, assertIsOneOfOrUndefined, assertIsSubset, assertMultiple, assertOrUndefined, assertPositive, assertRange, assertRangeOrUndefined, backtick, beginMarkedContent, beginText, breakTextIntoLines, byAscendingId, bytesFor, canBeConvertedToUint8Array, charAtIndex, charFromCode, charFromHexCode, charSplit, cleanText, clip, clipEvenOdd, closePath, cmyk, colorToComponents, componentsToColor, concatTransformationMatrix, copyStringIntoBuffer, createPDFAcroField, createPDFAcroFields, createTypeErrorMsg, createValueErrorMsg, decodeFromBase64$1 as decodeFromBase64, decodeFromBase64DataUri, decodePDFRawStream, defaultButtonAppearanceProvider, defaultCheckBoxAppearanceProvider, defaultDropdownAppearanceProvider, defaultOptionListAppearanceProvider, defaultRadioGroupAppearanceProvider, defaultTextFieldAppearanceProvider, degrees, degreesToRadians, drawButton, drawCheckBox, drawCheckMark, drawEllipse, drawEllipsePath, drawImage, drawLine, drawLinesOfText, drawObject, drawOptionList, drawPage, drawRadioButton, drawRectangle, drawSvgPath, drawText, drawTextField, drawTextLines, encodeToBase64, endMarkedContent, endPath, endText, error, escapeRegExp, escapedNewlineChars, extractText, extractTextFromPage, fill, fillAndStroke, findLastMatch, getType, grayscale, hasSurrogates, hasUtf16BOM, highSurrogate, isNewlineChar, isStandardFont, isType, isWithinBMP, last, layoutCombedText, layoutMultilineText, layoutSinglelineText, lineSplit, lineTo, lowSurrogate, mergeIntoTypedArray, mergeLines, mergeUint8Arrays, moveText, moveTo, newlineChars, nextLine, normalizeAppearance, numberToString, padStart$1 as padStart, parseDate, pdfDocEncodingDecode, pluckIndices, popGraphicsState, pushGraphicsState, radians, radiansToDegrees, range, rectangle, rectanglesAreEqual, reduceRotation, removeTextContaining, restoreDashPattern, reverseArray, rgb, rotateAndSkewTextDegreesAndTranslate, rotateAndSkewTextRadiansAndTranslate, rotateDegrees, rotateInPlace, rotateRadians, rotateRectangle, scale, setCharacterSpacing, setCharacterSqueeze, setDashPattern, setFillingCmykColor, setFillingColor, setFillingGrayscaleColor, setFillingRgbColor, setFontAndSize, setGraphicsState, setLineCap, setLineHeight, setLineJoin, setLineWidth, setStrokingCmykColor, setStrokingColor, setStrokingGrayscaleColor, setStrokingRgbColor, setTextMatrix, setTextRenderingMode, setTextRise, setWordSpacing, showText, singleQuote, sizeInBytes, skewDegrees, skewRadians, sortedUniq, square, stroke, sum, toCharCode, toCodePoint, toDegrees, toHexString, toHexStringOfMinLength, toRadians, toUint8Array, translate, typedArrayFor, utf16Decode, utf16Encode, utf8Encode, values, waitForTick };
|
|
26039
26633
|
//# sourceMappingURL=pdf-lib.esm.js.map
|