Issue work (#113)

* Add web support (Fixes #108) * Support badly formatted PDF files (Fixes #36) * Analysis updates * Add test for the ByteStream warning
NicolaVerbeeck · Jun 3, 2024 · 48ce78b · 48ce78b
1 parent 836871b
commit 48ce78b
Show file tree

Hide file tree

Showing 35 changed files with 276 additions and 152 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,9 @@
+## 2.0.0
+
+- Add web support
+- Support badly formatted PDFs that have only 19 byte long xref sections
+- **Breaking** FileStream has moved to dart_pdf_reader_io library
+
 ## 1.0.1
 
 - Added funding to pubspec.yaml
@@ -17,7 +23,8 @@
 ## 0.5.0
 
 - Add support for web by using the archive package. (#48)
-- **Breaking**: EOFException and ParseException now no longer implement dart:io's IOException, just base Exception. (#48)
+- **Breaking**: EOFException and ParseException now no longer implement dart:io's IOException, just base Exception. (
+  #48)
 
 ## 0.4.3
 

diff --git a/analysis_options.yaml b/analysis_options.yaml
@@ -12,3 +12,16 @@ linter:
     - prefer_const_constructors
     - prefer_final_locals
     - omit_local_variable_types
+    - prefer_relative_imports
+    - avoid_print
+    - avoid_unnecessary_containers
+    - avoid_web_libraries_in_flutter
+    - no_logic_in_create_state
+    - prefer_const_constructors_in_immutables
+    - prefer_const_declarations
+    - prefer_const_literals_to_create_immutables
+    - sized_box_for_whitespace
+    - sort_child_properties_last
+    - use_build_context_synchronously
+    - use_full_hex_values_for_flutter_colors
+    - use_key_in_widget_constructors
diff --git a/example/example.dart b/example/example.dart
@@ -1,3 +1,5 @@
+// ignore_for_file: avoid_print
+
 import 'dart:io';
 
 import 'package:dart_pdf_reader/dart_pdf_reader.dart';

diff --git a/lib/dart_pdf_reader.dart b/lib/dart_pdf_reader.dart
@@ -11,5 +11,4 @@ export 'src/parser/object_resolver.dart';
 export 'src/parser/pdf_parser.dart' show PDFParser;
 export 'src/utils/byte_stream.dart';
 export 'src/utils/cache/buffered_random_access_stream.dart';
-export 'src/utils/file_stream.dart';
 export 'src/utils/random_access_stream.dart';
diff --git a/lib/dart_pdf_reader_io.dart b/lib/dart_pdf_reader_io.dart
@@ -0,0 +1,4 @@
+library dart_pdf_reader_io;
+
+export 'dart_pdf_reader.dart';
+export 'src/utils/file_stream.dart';
diff --git a/lib/src/model/indirect_object_table.dart b/lib/src/model/indirect_object_table.dart
@@ -1,5 +1,5 @@
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/xref_reader.dart';
+import 'pdf_types.dart';
+import '../parser/xref_reader.dart';
 
 class IndirectObjectTable {
   final XRefTable _xrefTable;

diff --git a/lib/src/model/pdf_constants.dart b/lib/src/model/pdf_constants.dart
@@ -1,11 +1,11 @@
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
+import 'pdf_types.dart';
 import 'package:meta/meta.dart';
 
 /// Collection of names used in PDF files
 @immutable
 final class PDFNames {
   // coverage:ignore-start
-  PDFNames._();
+  const PDFNames._();
 
   // coverage:ignore-end
 

diff --git a/lib/src/model/pdf_document.dart b/lib/src/model/pdf_document.dart
@@ -1,7 +1,7 @@
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/model/pdf_document_catalog.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
+import 'pdf_constants.dart';
+import 'pdf_document_catalog.dart';
+import 'pdf_types.dart';
+import '../parser/object_resolver.dart';
 
 /// Holds the data for the PDF document.
 class PDFDocument {

diff --git a/lib/src/model/pdf_document_catalog.dart b/lib/src/model/pdf_document_catalog.dart
@@ -1,9 +1,9 @@
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/model/pdf_document.dart';
-import 'package:dart_pdf_reader/src/model/pdf_outline.dart';
-import 'package:dart_pdf_reader/src/model/pdf_page.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
+import 'pdf_constants.dart';
+import 'pdf_document.dart';
+import 'pdf_outline.dart';
+import 'pdf_page.dart';
+import 'pdf_types.dart';
+import '../parser/object_resolver.dart';
 
 /// The document catalog describing the document
 class PDFDocumentCatalog {

diff --git a/lib/src/model/pdf_outline.dart b/lib/src/model/pdf_outline.dart
@@ -1,4 +1,4 @@
-import 'package:dart_pdf_reader/dart_pdf_reader.dart';
+import '../../dart_pdf_reader.dart';
 import 'package:meta/meta.dart';
 
 /// Action types for pdf outlines

diff --git a/lib/src/model/pdf_page.dart b/lib/src/model/pdf_page.dart
@@ -1,10 +1,10 @@
 import 'dart:math';
 
-import 'package:dart_pdf_reader/src/error/exceptions.dart';
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/model/pdf_document.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
+import '../error/exceptions.dart';
+import 'pdf_constants.dart';
+import 'pdf_document.dart';
+import 'pdf_types.dart';
+import '../parser/object_resolver.dart';
 
 /// Pages tree root of the document
 class PDFPages {

diff --git a/lib/src/model/pdf_types.dart b/lib/src/model/pdf_types.dart
@@ -4,11 +4,11 @@ import 'dart:typed_data';
 
 import 'package:charset/charset.dart';
 import 'package:collection/collection.dart';
-import 'package:dart_pdf_reader/src/error/exceptions.dart';
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
-import 'package:dart_pdf_reader/src/utils/filter/stream_filter.dart';
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
+import '../error/exceptions.dart';
+import 'pdf_constants.dart';
+import '../parser/object_resolver.dart';
+import '../utils/filter/stream_filter.dart';
+import '../utils/random_access_stream.dart';
 import 'package:meta/meta.dart';
 
 /// Base class for all PDF objects.

diff --git a/lib/src/parser/indirect_object_parser.dart b/lib/src/parser/indirect_object_parser.dart
@@ -1,14 +1,14 @@
-import 'package:dart_pdf_reader/src/error/exceptions.dart';
-import 'package:dart_pdf_reader/src/model/indirect_object_table.dart';
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
-import 'package:dart_pdf_reader/src/parser/pdf_object_parser.dart';
-import 'package:dart_pdf_reader/src/parser/token_stream.dart';
-import 'package:dart_pdf_reader/src/parser/xref_reader.dart';
-import 'package:dart_pdf_reader/src/utils/byte_stream.dart';
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
-import 'package:dart_pdf_reader/src/utils/reader_helper.dart';
+import '../error/exceptions.dart';
+import '../model/indirect_object_table.dart';
+import '../model/pdf_constants.dart';
+import '../model/pdf_types.dart';
+import 'object_resolver.dart';
+import 'pdf_object_parser.dart';
+import 'token_stream.dart';
+import 'xref_reader.dart';
+import '../utils/byte_stream.dart';
+import '../utils/random_access_stream.dart';
+import '../utils/reader_helper.dart';
 
 class IndirectObjectParser {
   final RandomAccessStream _buffer;

diff --git a/lib/src/parser/object_resolver.dart b/lib/src/parser/object_resolver.dart
@@ -1,6 +1,6 @@
-import 'package:dart_pdf_reader/src/model/indirect_object_table.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/indirect_object_parser.dart';
+import '../model/indirect_object_table.dart';
+import '../model/pdf_types.dart';
+import 'indirect_object_parser.dart';
 
 class ObjectResolver {
   final IndirectObjectParser _indirectObjectParser;

diff --git a/lib/src/parser/pdf_object_parser.dart b/lib/src/parser/pdf_object_parser.dart
@@ -1,8 +1,8 @@
-import 'package:dart_pdf_reader/dart_pdf_reader.dart';
-import 'package:dart_pdf_reader/src/parser/indirect_object_parser.dart';
-import 'package:dart_pdf_reader/src/parser/token_stream.dart';
-import 'package:dart_pdf_reader/src/utils/list_extensions.dart';
-import 'package:dart_pdf_reader/src/utils/reader_helper.dart';
+import '../../dart_pdf_reader.dart';
+import 'indirect_object_parser.dart';
+import 'token_stream.dart';
+import '../utils/list_extensions.dart';
+import '../utils/reader_helper.dart';
 
 class PDFObjectParser {
   final RandomAccessStream _buffer;

diff --git a/lib/src/parser/pdf_parser.dart b/lib/src/parser/pdf_parser.dart
@@ -1,13 +1,13 @@
-import 'package:dart_pdf_reader/src/model/indirect_object_table.dart';
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/model/pdf_document.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/indirect_object_parser.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
-import 'package:dart_pdf_reader/src/parser/pdf_object_parser.dart';
-import 'package:dart_pdf_reader/src/parser/xref_reader.dart';
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
-import 'package:dart_pdf_reader/src/utils/reader_helper.dart';
+import '../model/indirect_object_table.dart';
+import '../model/pdf_constants.dart';
+import '../model/pdf_document.dart';
+import '../model/pdf_types.dart';
+import 'indirect_object_parser.dart';
+import 'object_resolver.dart';
+import 'pdf_object_parser.dart';
+import 'xref_reader.dart';
+import '../utils/random_access_stream.dart';
+import '../utils/reader_helper.dart';
 import 'package:meta/meta.dart';
 
 /// Parses a PDF document from a [RandomAccessStream].
@@ -30,11 +30,12 @@ class PDFParser {
     final objectParser = IndirectObjectParser(_buffer, table);
 
     PDFDictionary? mainTrailer;
-    final first = true;
+    var first = true;
     while (true) {
       final trailer = (first && parsedXRefTrailer != null)
           ? parsedXRefTrailer
           : await parseTrailer(objectParser, _buffer);
+      first = false;
       mainTrailer ??= trailer;
       final prev = trailer[PDFNames.prev] as PDFNumber?;
       if (prev == null) break;

diff --git a/lib/src/parser/token_stream.dart b/lib/src/parser/token_stream.dart
@@ -1,4 +1,4 @@
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
+import '../utils/random_access_stream.dart';
 
 typedef CharCode = int;
 

diff --git a/lib/src/parser/xref_reader.dart b/lib/src/parser/xref_reader.dart
@@ -1,17 +1,17 @@
 import 'dart:math';
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/src/error/exceptions.dart';
-import 'package:dart_pdf_reader/src/model/indirect_object_table.dart';
-import 'package:dart_pdf_reader/src/model/pdf_constants.dart';
-import 'package:dart_pdf_reader/src/model/pdf_types.dart';
-import 'package:dart_pdf_reader/src/parser/indirect_object_parser.dart';
-import 'package:dart_pdf_reader/src/parser/object_resolver.dart';
-import 'package:dart_pdf_reader/src/parser/pdf_object_parser.dart';
-import 'package:dart_pdf_reader/src/parser/token_stream.dart';
-import 'package:dart_pdf_reader/src/utils/filter/direct_byte_stream.dart';
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
-import 'package:dart_pdf_reader/src/utils/reader_helper.dart';
+import '../error/exceptions.dart';
+import '../model/indirect_object_table.dart';
+import '../model/pdf_constants.dart';
+import '../model/pdf_types.dart';
+import 'indirect_object_parser.dart';
+import 'object_resolver.dart';
+import 'pdf_object_parser.dart';
+import 'token_stream.dart';
+import '../utils/filter/direct_byte_stream.dart';
+import '../utils/random_access_stream.dart';
+import '../utils/reader_helper.dart';
 import 'package:meta/meta.dart';
 
 @immutable
@@ -244,10 +244,22 @@ class _XRefSubsectionReader {
     final numEntries = int.parse(parts[1]);
 
     final entries = <XRefEntry>[];
-    final lineBytes = Uint8List(20);
+    var readSize = 20;
+    final lineBytes = Uint8List(readSize);
     var id = startIndex;
     for (var i = 0; i < numEntries; ++i) {
-      await stream.readBuffer(20, lineBytes);
+      await stream.readBuffer(readSize, lineBytes);
+
+      if (i == 0) {
+        final last = lineBytes.last;
+        if (last >= 0x30 && last <= 0x39) {
+          // Some lines 19 bytes long even though that is not the standard
+          // To support this, start using 19 by tes and step 1 back
+          await stream.seek((await stream.position) - 1);
+          // Read 19 bytes from now on
+          readSize = 19;
+        }
+      }
 
       final offset = int.parse(String.fromCharCodes(lineBytes.getRange(0, 10)));
       final generation =

diff --git a/lib/src/utils/byte_stream.dart b/lib/src/utils/byte_stream.dart
@@ -1,7 +1,7 @@
 import 'dart:math';
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
+import 'random_access_stream.dart';
 
 /// Implementation of [RandomAccessStream] which reads from a list of bytes
 class ByteStream extends RandomAccessStream {

diff --git a/lib/src/utils/cache/buffered_random_access_stream.dart b/lib/src/utils/cache/buffered_random_access_stream.dart
@@ -1,9 +1,9 @@
 import 'dart:math';
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/src/utils/byte_stream.dart';
-import 'package:dart_pdf_reader/src/utils/cache/lru_map.dart';
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
+import '../byte_stream.dart';
+import '../random_access_stream.dart';
+import 'lru_map.dart';
 
 /// Implementation of [RandomAccessStream] which buffers reads from another stream
 /// This is useful for improving performance when reading from a slow stream
@@ -30,11 +30,15 @@ class BufferedRandomAccessStream extends RandomAccessStream {
     int maxNumBlocks = 10,
   })  : _blockSize = blockSize,
         _cache = LRUMap(maxNumBlocks) {
-    if (_stream is ByteStream) {
-      print(
-        'Warning: BufferedRandomAccessStream is not recommended for ByteStream',
-      );
-    }
+    assert(() {
+      if (_stream is ByteStream) {
+        // ignore: avoid_print
+        print(
+          'Warning: BufferedRandomAccessStream is not recommended for ByteStream',
+        );
+      }
+      return true;
+    }());
   }
 
   @override

diff --git a/lib/src/utils/file_stream.dart b/lib/src/utils/file_stream.dart
@@ -1,7 +1,7 @@
 import 'dart:io';
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/src/utils/random_access_stream.dart';
+import 'random_access_stream.dart';
 
 /// Implementation of [RandomAccessStream] which reads from a file
 /// Currently this does not perform smart buffering and can be quite slow

diff --git a/lib/src/utils/filter/stream_filter.dart b/lib/src/utils/filter/stream_filter.dart
@@ -1,9 +1,9 @@
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/dart_pdf_reader.dart';
-import 'package:dart_pdf_reader/src/utils/filter/direct_byte_stream.dart';
+import '../../../dart_pdf_reader.dart';
+import 'direct_byte_stream.dart';
 import 'package:archive/archive.dart';
-import 'package:dart_pdf_reader/src/utils/list_extensions.dart';
+import '../list_extensions.dart';
 
 part 'ascii_85_decode_filter.dart';
 part 'ascii_hex_decode_filter.dart';

diff --git a/lib/src/utils/random_access_stream.dart b/lib/src/utils/random_access_stream.dart
@@ -1,6 +1,6 @@
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/src/error/exceptions.dart';
+import '../error/exceptions.dart';
 
 /// An abstraction of a stream of bytes that can be read from.
 abstract class RandomAccessStream {

diff --git a/lib/src/utils/reader_helper.dart b/lib/src/utils/reader_helper.dart
@@ -1,7 +1,7 @@
 import 'dart:typed_data';
 
-import 'package:dart_pdf_reader/dart_pdf_reader.dart';
-import 'package:dart_pdf_reader/src/parser/token_stream.dart';
+import '../../dart_pdf_reader.dart';
+import '../parser/token_stream.dart';
 
 abstract class ReaderHelper {
   /// Try to read the first non-empty line from the buffer, stripping comments

diff --git a/pubspec.yaml b/pubspec.yaml
@@ -1,9 +1,9 @@
 name: dart_pdf_reader
 description: Small pure-dart library for parsing PDF files. Supports reading all pdf structures
-version: 1.0.1
+version: 2.0.0
 repository: https://github.com/NicolaVerbeeck/dart_pdf_reader
 issue_tracker: https://github.com/NicolaVerbeeck/dart_pdf_reader/issues
-topics: [pdf, parser]
+topics: [ pdf, parser ]
 
 environment:
   sdk: '>=3.0.0 <4.0.0'
@@ -15,7 +15,7 @@ dependencies:
   meta: '>=1.9.1 < 2.0.0'
 
 dev_dependencies:
-  lints: ">=2.0.0 <5.0.0"
+  lints: ^4.0.0
   test: ^1.21.0
   mocktail: ^1.0.0
   convert: ^3.1.1