lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-10-14 10:55:04 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

encapsulation for internal classes, remove old code, document public api

Browse Source
This commit is contained in:
Eliot Jones
2018-01-07 12:37:48 +00:00
parent ad1ef0e167
commit bb93484909
58 changed files with 181 additions and 1117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/UglyToad.Pdf.Tests/Parser/Parts/ThrowingReader.cs
View File

@@ -3,7 +3,7 @@
using System;
using IO;
public class ThrowingReader : IRandomAccessRead
internal class ThrowingReader : IRandomAccessRead
{
private readonly IRandomAccessRead reader;

2
src/UglyToad.Pdf.Tests/StringBytesTestConverter.cs
View File

@@ -5,7 +5,7 @@
using Pdf.Tokenization.Scanner;
using Pdf.Util;
public static class StringBytesTestConverter
internal static class StringBytesTestConverter
{
public static Result Convert(string s, bool readFirst = true)
{

2
src/UglyToad.Pdf/Content/CropBox.cs
View File

@@ -7,7 +7,7 @@
/// <summary>
/// Defines the visible region, contents expanding beyond the crop box should be clipped.
/// </summary>
public class CropBox
internal class CropBox
{
[NotNull]
public PdfRectangle Bounds { get; }

5
src/UglyToad.Pdf/Content/DocumentInformation.cs
View File

@@ -70,6 +70,9 @@
representation = builder.ToString() ?? string.Empty;
}
/// <summary>
/// Gets a string representing this document information. <see langword="null"/> entries are not shown.
/// </summary>
public override string ToString()
{
return representation;
@@ -82,7 +85,7 @@
return;
}
builder.Append(name).Append(": ").Append(value).Append(";");
builder.Append(name).Append(": ").Append(value).Append("; ");
}
}
}

2
src/UglyToad.Pdf/Content/MediaBox.cs
View File

@@ -9,7 +9,7 @@
/// <remarks>
/// See table 3.27 from the PDF specification version 1.7.
/// </remarks>
public class MediaBox
internal class MediaBox
{
///<summary>
/// User space units per inch.

3
src/UglyToad.Pdf/Content/Page.cs
View File

@@ -4,6 +4,9 @@
using System.Collections.Generic;
using System.Linq;
/// <summary>
/// Contains the content and provides access to methods of a single page in the <see cref="PdfDocument"/>.
/// </summary>
public class Page
{
/// <summary>

54
src/UglyToad.Pdf/Content/PageSize.cs
View File

@@ -3,24 +3,78 @@
using System.Collections.Generic;
using Geometry;
/// <summary>
/// The corresponding named size of the <see cref="Page"/>.
/// </summary>
public enum PageSize
{
/// <summary>
/// Unknown page size, did not match a defined page size.
/// </summary>
Custom = 0,
/// <summary>
/// The ISO 216 A0 page size.
/// </summary>
A0 = 3,
/// <summary>
/// The ISO 216 A1 page size.
/// </summary>
A1 = 4,
/// <summary>
/// The ISO 216 A2 page size.
/// </summary>
A2 = 5,
/// <summary>
/// The ISO 216 A3 page size.
/// </summary>
A3 = 6,
/// <summary>
/// The ISO 216 A4 page size.
/// </summary>
A4 = 7,
/// <summary>
/// The ISO 216 A5 page size.
/// </summary>
A5 = 8,
/// <summary>
/// The ISO 216 A6 page size.
/// </summary>
A6 = 9,
/// <summary>
/// The ISO 216 A7 page size.
/// </summary>
A7 = 10,
/// <summary>
/// The ISO 216 A8 page size.
/// </summary>
A8 = 11,
/// <summary>
/// The ISO 216 A9 page size.
/// </summary>
A9 = 12,
/// <summary>
/// The ISO 216 A10 page size.
/// </summary>
A10 = 13,
/// <summary>
/// The North American Letter page size.
/// </summary>
Letter = 14,
/// <summary>
/// The North American Legal page size.
/// </summary>
Legal = 15,
/// <summary>
/// The North American Ledger page size.
/// </summary>
Ledger = 16,
/// <summary>
/// The North American Tabloid page size.
/// </summary>
Tabloid = 17,
/// <summary>
/// The North American Executive page size.
/// </summary>
Executive = 18
}

2
src/UglyToad.Pdf/Content/PageTreeMembers.cs
View File

@@ -5,7 +5,7 @@
/// <summary>
/// Contains the values inherited from the Page Tree for this page.
/// </summary>
public class PageTreeMembers
internal class PageTreeMembers
{
public MediaBox GetMediaBox()
{

2
src/UglyToad.Pdf/ContentStream/IndirectReference.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.ContentStream
{
public struct IndirectReference
internal struct IndirectReference
{
public long ObjectNumber { get; }

2
src/UglyToad.Pdf/Core/ICosStreamWriter.cs
View File

@@ -2,7 +2,7 @@
{
using System.IO;
public interface ICosStreamWriter
internal interface ICosStreamWriter
{
void WriteToPdfStream(BinaryWriter output);
}

2
src/UglyToad.Pdf/Core/IDeepCloneable.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Core
{
public interface IDeepCloneable<out T>
internal interface IDeepCloneable<out T>
{
T DeepClone();
}

4
src/UglyToad.Pdf/Core/TransformationMatrix.cs
View File

@@ -148,7 +148,7 @@
{
var xScale = A;
/**
/*
* BM: if the trm is rotated, the calculation is a little more complicated
*
* The rotation matrix multiplied with the scaling matrix is:
@@ -161,7 +161,7 @@
*
* sqrt(M(0,0)^2+M(0,1)^2) =
* sqrt(x2*cos2+x2*sin2) =
* sqrt(x2*(cos2+sin2)) = <- here is the trick cos2+sin2 is one
* sqrt(x2*(cos2+sin2)) = (here is the trick cos2+sin2 = 1)
* sqrt(x2) =
* abs(x)
*/

3
src/UglyToad.Pdf/Cos/CosArray.cs
View File

@@ -15,11 +15,12 @@
* limitations under the License.
*/
/**
/*
* An array of PDFBase objects as part of the PDF document.
*
* @author Ben Litchfield
*/
namespace UglyToad.Pdf.Cos
{
using System;

131
src/UglyToad.Pdf/Cos/CosDictionary.cs
View File

@@ -748,136 +748,7 @@
}
return retval;
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a name and convert it to
* a string. Null is returned if the entry does not exist in the dictionary or if the date was invalid.
*
* @param key The key to the item in the dictionary.
* @return The name converted to a date.
*/
public DateTime? getDate(String key)
{
return getDate(CosName.Create(key));
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a name and convert it to
* a string. Null is returned if the entry does not exist in the dictionary or if the date was invalid.
*
* @param key The key to the item in the dictionary.
* @return The name converted to a date.
*/
public DateTime? getDate(CosName key)
{
CosBase baseObj = getDictionaryObject(key);
if (baseObj is CosString)
{
return DateConverter.toCalendar((CosString)baseObj);
}
return null;
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a date. Null is returned
* if the entry does not exist in the dictionary or if the date was invalid.
*
* @param key The key to the item in the dictionary.
* @param defaultValue The default value to return.
* @return The name converted to a date.
*/
public DateTime? getDate(String key, DateTime defaultValue)
{
return getDate(CosName.Create(key), defaultValue);
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a date. Null is returned
* if the entry does not exist in the dictionary or if the date was invalid.
*
* @param key The key to the item in the dictionary.
* @param defaultValue The default value to return.
* @return The name converted to a date.
*/
public DateTime? getDate(CosName key, DateTime? defaultValue)
{
var retval = getDate(key);
if (retval == null)
{
retval = defaultValue;
}
return retval;
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a name and convert it to
* a string. Null is returned if the entry does not exist in the dictionary.
*
* @param embedded The embedded dictionary to get.
* @param key The key to the item in the dictionary.
* @return The name converted to a string.
* @ If there is an error converting to a date.
*/
public DateTime? getEmbeddedDate(String embedded, String key)
{
return getEmbeddedDate(embedded, CosName.Create(key), null);
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a name and convert it to
* a string. Null is returned if the entry does not exist in the dictionary.
*
* @param embedded The embedded dictionary to get.
* @param key The key to the item in the dictionary.
* @return The name converted to a string.
*
* @ If there is an error converting to a date.
*/
public DateTime? getEmbeddedDate(String embedded, CosName key)
{
return getEmbeddedDate(embedded, key, null);
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a date. Null is returned
* if the entry does not exist in the dictionary.
*
* @param embedded The embedded dictionary to get.
* @param key The key to the item in the dictionary.
* @param defaultValue The default value to return.
* @return The name converted to a string.
* @ If there is an error converting to a date.
*/
public DateTime? getEmbeddedDate(String embedded, String key, DateTime? defaultValue)
{
return getEmbeddedDate(embedded, CosName.Create(key), defaultValue);
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a date. Null is returned
* if the entry does not exist in the dictionary.
*
* @param embedded The embedded dictionary to get.
* @param key The key to the item in the dictionary.
* @param defaultValue The default value to return.
* @return The name converted to a string.
* @ If there is an error converting to a date.
*/
public DateTime? getEmbeddedDate(String embedded, CosName key, DateTime? defaultValue)
{
var retval = defaultValue;
CosDictionary eDic = (CosDictionary)getDictionaryObject(embedded);
if (eDic != null)
{
retval = eDic.getDate(key, defaultValue);
}
return retval;
}
/**
* This is a convenience method that will get the dictionary object that is expected to be a cos bool and convert
* it to a primitive bool.

33
src/UglyToad.Pdf/Cos/CosNumberFactory.cs
View File

@@ -2,7 +2,7 @@
{
using System;
public static class CosNumberFactory
internal static class CosNumberFactory
{
/**
* This factory method will get the appropriate number object.
@@ -15,7 +15,7 @@
*/
public static ICosNumber get(string value)
{
if (value.Length == 1)
if (value.Length == 1)
{
char digit = value[0];
if ('0' <= digit && digit <= '9')
@@ -31,25 +31,26 @@
{
throw new ArgumentException($"Not a number: {value}");
}
}
else if (value.IndexOf('.') == -1 && (value.ToLower().IndexOf('e') == -1))
}
else
{
try
if (value.IndexOf('.') == -1 && (value.ToLower().IndexOf('e') == -1))
{
if (value[0] == '+')
try
{
return CosInt.Get(long.Parse(value.Substring(1)));
if (value[0] == '+')
{
return CosInt.Get(long.Parse(value.Substring(1)));
}
return CosInt.Get(long.Parse(value));
}
catch (FormatException)
{
// might be a huge number, see PDFBOX-3116
return new CosFloat(value);
}
return CosInt.Get(long.Parse(value));
}
catch (FormatException e)
{
// might be a huge number, see PDFBOX-3116
return new CosFloat(value);
}
}
else
{
return new CosFloat(value);
}
}

2
src/UglyToad.Pdf/Cos/CrossReferenceType.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Cos
{
public enum CrossReferenceType
internal enum CrossReferenceType
{
Table,
Stream

2
src/UglyToad.Pdf/Cos/ICosNumber.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Cos
{
public interface ICosNumber
internal interface ICosNumber
{
float AsFloat();

2
src/UglyToad.Pdf/Filters/PngPredictor.cs
View File

@@ -5,7 +5,7 @@
using System.IO;
using IO;
public class PngPredictor : IPngPredictor
internal class PngPredictor : IPngPredictor
{
public byte[] Decode(byte[] inputBytes, int predictor, int colors, int bitsPerComponent, int columns)
{

2
src/UglyToad.Pdf/Fonts/CharacterIdentifierSystemInfo.cs
View File

@@ -5,7 +5,7 @@
/// <summary>
/// Specifies the character collection associated with the <see cref="ICidFont"/> (CIDFont).
/// </summary>
public struct CharacterIdentifierSystemInfo
internal struct CharacterIdentifierSystemInfo
{
/// <summary>
/// Identifies the issuer of the character collection.

7
src/UglyToad.Pdf/Fonts/CidFonts/CharacterIdentifierToGlyphIdentifierMap.cs
View File

@@ -1,7 +0,0 @@
namespace UglyToad.Pdf.Fonts.CidFonts
{
public class CharacterIdentifierToGlyphIdentifierMap
{
}
}

2
src/UglyToad.Pdf/Fonts/CidFonts/CidFontType.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Fonts.CidFonts
{
public enum CidFontType
internal enum CidFontType
{
/// <summary>
/// Glyph descriptions based on Adobe Type 1 format.

2
src/UglyToad.Pdf/Fonts/CidFonts/VerticalVectorComponents.cs
View File

@@ -3,7 +3,7 @@
/// <summary>
/// Equivalent to the DW2 array in the font dictionary for vertical fonts.
/// </summary>
public struct VerticalVectorComponents
internal struct VerticalVectorComponents
{
public decimal Position { get; }

2
src/UglyToad.Pdf/Fonts/Cmap/CidCharacterMapping.cs
View File

@@ -3,7 +3,7 @@
/// <summary>
/// Maps from a single character code to its CID.
/// </summary>
public struct CidCharacterMapping
internal struct CidCharacterMapping
{
/// <summary>
/// The character code.

2
src/UglyToad.Pdf/Fonts/Cmap/CidRange.cs
View File

@@ -5,7 +5,7 @@
/// <summary>
/// Associates the beginning and end of a range of character codes with the starting CID for the range.
/// </summary>
public struct CidRange
internal struct CidRange
{
/// <summary>
/// The beginning of the range of character codes.

2
src/UglyToad.Pdf/Fonts/Cmap/CodespaceRange.cs
View File

@@ -6,7 +6,7 @@
/// <summary>
/// A codespace range is specified by a pair of codes of some particular length giving the lower and upper bounds of that range.
/// </summary>
public class CodespaceRange
internal class CodespaceRange
{
/// <summary>
/// The lower-bound of this range.

20
src/UglyToad.Pdf/Fonts/Simple/TrueTypeSimpleFont.cs
View File

@@ -71,26 +71,6 @@
value = GlyphList.AdobeGlyphList.NameToUnicode(encodedCharacterName);
return true;
if (!ToUnicode.CanMapToUnicode)
{
try
{
if (encoding != null)
{
}
value = ((char) characterCode).ToString();
return true;
}
catch (Exception)
{
return false;
}
}
return ToUnicode.TryGet(characterCode, out value);
}
public PdfVector GetDisplacement(int characterCode)

31
src/UglyToad.Pdf/Fonts/TextObjectComponentType.cs
View File

@@ -1,31 +0,0 @@
namespace UglyToad.Pdf.Fonts
{
public enum TextObjectComponentType
{
BeginText,
EndText,
TextFont,
SetTextMatrix,
MoveTextPosition,
MoveTextPositionAndSetLeading,
ShowText,
ShowTextWithIndividualGlyphPositioning,
SetTextLeading,
SetTextRenderingMode,
SetTextRise,
SetWordSpacing,
SetHorizontalTextScaling,
MoveToNextLineStart,
SetCharacterSpacing,
Numeric,
String,
Font,
Array,
SetGrayNonStroking,
SetGrayStroking,
SetLineWidth,
SetClippingPathNonZeroWinding,
SetClippingPathEvenOdd,
MoveNextLineAndShowText
}
}

12
src/UglyToad.Pdf/Geometry/PdfPoint.cs
View File

@@ -25,24 +25,36 @@
/// </summary>
public decimal Y { get; }
/// <summary>
/// Create a new <see cref="PdfPoint"/> at this position.
/// </summary>
public PdfPoint(decimal x, decimal y)
{
X = x;
Y = y;
}
/// <summary>
/// Create a new <see cref="PdfPoint"/> at this position.
/// </summary>
public PdfPoint(int x, int y)
{
X = x;
Y = y;
}
/// <summary>
/// Create a new <see cref="PdfPoint"/> at this position.
/// </summary>
public PdfPoint(double x, double y)
{
X = (decimal)x;
Y = (decimal)y;
}
/// <summary>
/// Get a string representation of this point.
/// </summary>
public override string ToString()
{
return $"(x:{X}, y:{Y})";

2
src/UglyToad.Pdf/Geometry/PdfRectangle.cs
View File

@@ -2,7 +2,7 @@
{
using System;
public class PdfRectangle
internal class PdfRectangle
{
public PdfPoint TopLeft { get; }

2
src/UglyToad.Pdf/Geometry/UserSpaceUnit.cs
View File

@@ -6,7 +6,7 @@
/// By default user space units correspond to 1/72nd of an inch (a typographic point).
/// The UserUnit entry in a page dictionary can define the space units as a different multiple of 1/72 (1 point).
/// </summary>
public struct UserSpaceUnit
internal struct UserSpaceUnit
{
public static readonly UserSpaceUnit Default = new UserSpaceUnit(1);

2
src/UglyToad.Pdf/Graphics/Core/LineDashPattern.cs
View File

@@ -2,7 +2,7 @@
{
using System;
public struct LineDashPattern
internal struct LineDashPattern
{
public int Phase { get; }

2
src/UglyToad.Pdf/ICosUpdateInfo.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf
{
public interface ICosUpdateInfo
internal interface ICosUpdateInfo
{
bool NeedsToBeUpdated { get; set; }
}

2
src/UglyToad.Pdf/IO/ByteArrayInputBytes.cs
View File

@@ -2,7 +2,7 @@
{
using System.Collections.Generic;
public class ByteArrayInputBytes : IInputBytes
internal class ByteArrayInputBytes : IInputBytes
{
private readonly IReadOnlyList<byte> bytes;

2
src/UglyToad.Pdf/IO/IInputBytes.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.IO
{
public interface IInputBytes
internal interface IInputBytes
{
int CurrentOffset { get; }

165
src/UglyToad.Pdf/IO/ISequentialSource.cs
View File

@@ -1,165 +0,0 @@
using System;
namespace UglyToad.Pdf.IO
{
public interface SequentialSource : IDisposable
{
/**
* Read a single byte of data.
*
* @return The byte of data that is being read.
* @throws IOException If there is an error while reading the data.
*/
int read();
/**
* Read a buffer of data.
*
* @param b The buffer to write the data to.
* @return The number of bytes that were actually read.
* @throws IOException If there was an error while reading the data.
*/
int read(byte[] b);
/**
* Read a buffer of data.
*
* @param b The buffer to write the data to.
* @param offset Offset into the buffer to start writing.
* @param length The amount of data to attempt to read.
* @return The number of bytes that were actually read.
* @throws IOException If there was an error while reading the data.
*/
int read(byte[] b, int offset, int length);
/**
* Returns offset of next byte to be returned by a read method.
*
* @return offset of next byte which will be returned with next {@link #read()} (if no more
* bytes are left it returns a value &gt;= length of source).
* @throws IOException If there was an error while reading the data.
*/
long getPosition();
/**
* This will peek at the next byte.
*
* @return The next byte on the stream, leaving it as available to read.
* @throws IOException If there is an error reading the next byte.
*/
int peek();
/**
* Unreads a single byte.
*
* @param b byte array to push back
* @throws IOException if there is an error while unreading
*/
void unread(int b);
/**
* Unreads an array of bytes.
*
* @param bytes byte array to be unread
* @throws IOException if there is an error while unreading
*/
void unread(byte[] bytes);
/**
* Unreads a portion of an array of bytes.
*
* @param bytes byte array to be unread
* @param start start index
* @param len number of bytes to be unread
* @throws IOException if there is an error while unreading
*/
void unread(byte[] bytes, int start, int len);
/**
* Reads a given number of bytes in its entirety.
*
* @param length the number of bytes to be read
* @return a byte array containing the bytes just read
* @throws IOException if an I/O error occurs while reading data
*/
byte[] readFully(int length);
/**
* Returns true if the end of the data source has been reached.
*
* @return true if we are at the end of the data.
* @throws IOException If there is an error reading the next byte.
*/
bool isEOF();
}
public class BufferSequentialSource : SequentialSource
{
private readonly IRandomAccessRead reader;
/**
* Constructor.
*
* @param reader The random access reader to wrap.
*/
public BufferSequentialSource(IRandomAccessRead reader)
{
this.reader = reader;
}
public int read()
{
return reader.Read();
}
public int read(byte[] b)
{
return reader.Read(b);
}
public int read(byte[] b, int offset, int length)
{
return reader.Read(b, offset, length);
}
public long getPosition()
{
return reader.GetPosition();
}
public int peek()
{
return reader.Peek();
}
public void unread(int b)
{
reader.Rewind(1);
}
public void unread(byte[] bytes)
{
reader.Rewind(bytes.Length);
}
public void unread(byte[] bytes, int start, int len)
{
reader.Rewind(len - start);
}
public byte[] readFully(int length)
{
return reader.ReadFully(length);
}
public bool isEOF()
{
return reader.IsEof();
}
public void Dispose()
{
reader.Dispose();
}
}
}

2
src/UglyToad.Pdf/IO/RandomAccess.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.IO
{
public interface RandomAccess : IRandomAccessRead, RandomAccessWrite
internal interface RandomAccess : IRandomAccessRead, RandomAccessWrite
{
// super interface for both read and write
}

2
src/UglyToad.Pdf/IO/RandomAccessBuffer.cs
View File

@@ -5,7 +5,7 @@ namespace UglyToad.Pdf.IO
{
using System.IO;
public class RandomAccessBuffer : RandomAccess
internal class RandomAccessBuffer : RandomAccess
{
// default chunk size is 1kb
private static readonly int DefaultChunkSize = 1024;

2
src/UglyToad.Pdf/IO/RandomAccessRead.cs
View File

@@ -2,7 +2,7 @@
{
using System;
public interface IRandomAccessRead : IDisposable
internal interface IRandomAccessRead : IDisposable
{
/**
* Read a single byte of data.

2
src/UglyToad.Pdf/IO/RandomAccessWrite.cs
View File

@@ -2,7 +2,7 @@
{
using System;
public interface RandomAccessWrite : IDisposable
internal interface RandomAccessWrite : IDisposable
{
/**
* Write a byte to the stream.

19
src/UglyToad.Pdf/Logging/ILog.cs
View File

@@ -2,12 +2,31 @@
namespace UglyToad.Pdf.Logging
{
/// <summary>
/// Logs internal messages from the PDF parsing process. Consumers can provide their own implementation
/// in the <see cref="ParsingOptions"/> to intercept log messages.
/// </summary>
public interface ILog
{
/// <summary>
/// Record an informational debug message.
/// </summary>
void Debug(string message);
/// <summary>
/// Record an informational debug message with exception.
/// </summary>
void Debug(string message, Exception ex);
/// <summary>
/// Record an warning message due to a non-error issue encountered in parsing.
/// </summary>
void Warn(string message);
/// <summary>
/// Record an error message due to an issue encountered in parsing.
/// </summary>
void Error(string message);
/// <summary>
/// Record an error message due to an issue encountered in parsing with exception.
/// </summary>
void Error(string message, Exception ex);
}

8
src/UglyToad.Pdf/Parser/FileStructure/XrefCosOffsetChecker.cs
View File

@@ -26,7 +26,7 @@
long objectOffset = objectEntry.Value;
// a negative offset number represents a object number itself
// see type 2 entry in xref stream
if (objectOffset != null && objectOffset >= 0
if (objectOffset >= 0
&& !checkObjectKeys(reader, objectKey, objectOffset))
{
//LOG.debug("Stop checking xref offsets as at least one (" + objectKey
@@ -58,7 +58,7 @@
return true;
}
}
catch (InvalidOperationException exception)
catch (InvalidOperationException)
{
// Swallow the exception, obviously there isn't any valid object number
}
@@ -180,7 +180,7 @@
foreach (var entry in xrefOffset)
{
long offset = entry.Value;
if (offset != null && offset < 0)
if (offset < 0)
{
CosObjectKey objStream = new CosObjectKey(-offset, 0);
if (!objStreams.Contains(objStream))
@@ -253,7 +253,7 @@
ObjectHelper.ReadObjectNumber(source);
ObjectHelper.ReadGenerationNumber(source);
}
catch (InvalidOperationException exception)
catch (InvalidOperationException)
{
// save the EOF marker as the following data is most likely some garbage
lastEOFMarker = tempMarker;

17
src/UglyToad.Pdf/ParsingOptions.cs
View File

@@ -2,10 +2,25 @@
{
using Logging;
/// <summary>
/// Configures options used by the parser when reading PDF documents.
/// </summary>
public class ParsingOptions
{
/// <summary>
/// Should the parser ignore issues where the document does not conform to the PDF specification?
/// </summary>
public bool UseLenientParsing { get; set; } = true;
public ILog Logger { get; set; } = new NoOpLog();
private ILog logger = new NoOpLog();
/// <summary>
/// The <see cref="ILog"/> used to record messages raised by the parsing process.
/// </summary>
public ILog Logger
{
get => logger ?? new NoOpLog();
set => logger = value;
}
}
}

6
src/UglyToad.Pdf/PdfDocument.cs
View File

@@ -6,10 +6,12 @@
using IO;
using Logging;
using Parser;
using Parser.FileStructure;
using Parser.Parts;
using Util.JetBrains.Annotations;
/// <inheritdoc />
/// <summary>
/// Provides access to document level information for this PDF document as well as access to the <see cref="T:UglyToad.Pdf.Content.Page" />s contained in the document.
/// </summary>
public class PdfDocument : IDisposable
{
[NotNull]

2
src/UglyToad.Pdf/Tokenization/Tokens/ArrayToken.cs
View File

@@ -3,7 +3,7 @@
using System.Collections.Generic;
using System.Text;
public class ArrayToken : IDataToken<IReadOnlyList<IToken>>
internal class ArrayToken : IDataToken<IReadOnlyList<IToken>>
{
public IReadOnlyList<IToken> Data { get; }

2
src/UglyToad.Pdf/Tokenization/Tokens/BooleanToken.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Tokenization.Tokens
{
public class BooleanToken : IDataToken<bool>
internal class BooleanToken : IDataToken<bool>
{
public static BooleanToken True { get; } = new BooleanToken(true);

2
src/UglyToad.Pdf/Tokenization/Tokens/CommentToken.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Tokenization.Tokens
{
public class CommentToken : IDataToken<string>
internal class CommentToken : IDataToken<string>
{
public string Data { get; }

2
src/UglyToad.Pdf/Tokenization/Tokens/HexToken.cs
View File

@@ -3,7 +3,7 @@ namespace UglyToad.Pdf.Tokenization.Tokens
using System.Collections.Generic;
using System.Text;
public class HexToken : IDataToken<string>
internal class HexToken : IDataToken<string>
{
private static readonly Dictionary<char, byte> HexMap = new Dictionary<char, byte>
{

2
src/UglyToad.Pdf/Tokenization/Tokens/IDataToken.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Tokenization.Tokens
{
public interface IDataToken<out T> : IToken
internal interface IDataToken<out T> : IToken
{
T Data { get; }
}

5
src/UglyToad.Pdf/Tokenization/Tokens/IToken.cs
View File

@@ -1,6 +1,9 @@
namespace UglyToad.Pdf.Tokenization.Tokens
{
public interface IToken
/// <summary>
/// A marker interface for tokens from the content.
/// </summary>
internal interface IToken
{
}
}

2
src/UglyToad.Pdf/Tokenization/Tokens/IndirectReferenceToken.cs
View File

@@ -2,7 +2,7 @@
{
using ContentStream;
public class IndirectReferenceToken : IDataToken<IndirectReference>
internal class IndirectReferenceToken : IDataToken<IndirectReference>
{
public IndirectReference Data { get; }

2
src/UglyToad.Pdf/Tokenization/Tokens/NullToken.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Tokenization.Tokens
{
public class NullToken : IDataToken<object>
internal class NullToken : IDataToken<object>
{
public static NullToken Instance { get; } = new NullToken();

2
src/UglyToad.Pdf/Tokenization/Tokens/NumericToken.cs
View File

@@ -3,7 +3,7 @@
using System;
using System.Globalization;
public class NumericToken : IDataToken<decimal>
internal class NumericToken : IDataToken<decimal>
{
public decimal Data { get; }

2
src/UglyToad.Pdf/Tokenization/Tokens/OperatorToken.cs
View File

@@ -2,7 +2,7 @@
{
using System.Collections.Generic;
public class OperatorToken : IDataToken<string>
internal class OperatorToken : IDataToken<string>
{
private static readonly Dictionary<string, string> PooledNames = new Dictionary<string, string>();

2
src/UglyToad.Pdf/Tokenization/Tokens/StringToken.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Tokenization.Tokens
{
public class StringToken : IDataToken<string>
internal class StringToken : IDataToken<string>
{
public string Data { get; }

695
src/UglyToad.Pdf/Util/DateConverter.cs
View File

@@ -1,695 +0,0 @@
namespace UglyToad.Pdf.Util
{
using System;
using System.Globalization;
using Cos;
internal class DateConverter
{
private DateConverter()
{
}
// milliseconds/1000 = seconds; seconds / 60 = minutes; minutes/60 = hours
private static readonly int MINUTES_PER_HOUR = 60;
private static readonly int SECONDS_PER_MINUTE = 60;
private static readonly int MILLIS_PER_MINUTE = SECONDS_PER_MINUTE * 1000;
private static readonly int MILLIS_PER_HOUR = MINUTES_PER_HOUR * MILLIS_PER_MINUTE;
private static readonly int HALF_DAY = 12 * MINUTES_PER_HOUR * MILLIS_PER_MINUTE, DAY = 2 * HALF_DAY;
/*
* The Date format is supposed to be the PDF_DATE_FORMAT, but other
* forms appear. These lists offer alternatives to be tried
* if parseBigEndianDate fails.
*
* The time zone offset generally trails the date string, so it is processed
* separately with parseTZoffset. (This does not preclude having time
* zones in the elements below; one does.)
*
* Alas, SimpleDateFormat is badly non-reentrant -- it modifies its
* calendar field (PDFBox-402), so these lists are strings to create
* SimpleDate format as needed.
*
* Some past entries have been elided because they duplicate existing
* entries. See the API for SimpleDateFormat, which says
* "For parsing, the number of pattern letters is ignored
* unless it's needed to separate two adjacent fields."
*
* toCalendar(String, String[]) tests to see that the entire input text
* has been consumed. Therefore the ordering of formats is important.
* If one format begins with the entirety of another, the longer
* must precede the other in the list.
*
* HH is for 0-23 hours and hh for 1-12 hours; an "a" field must follow "hh"
* Where year is yy, four digit years are accepted
* and two digit years are converted to four digits in the range
* [thisyear-79...thisyear+20]
*/
private static readonly String[] ALPHA_START_FORMATS =
{
"EEEE, dd MMM yy hh:mm:ss a",
"EEEE, MMM dd, yy hh:mm:ss a",
"EEEE, MMM dd, yy 'at' hh:mma", // Acrobat Net Distiller 1.0 for Windows
"EEEE, MMM dd, yy", // Acrobat Distiller 1.0.2 for Macintosh && PDFBOX-465
"EEEE MMM dd, yy HH:mm:ss", // ECMP5
"EEEE MMM dd HH:mm:ss z yy", // GNU Ghostscript 7.0.7
"EEEE MMM dd HH:mm:ss yy", // GNU Ghostscript 7.0.7 variant
};
private static readonly String[] DIGIT_START_FORMATS =
{
"dd MMM yy HH:mm:ss", // for 26 May 2000 11:25:00
"dd MMM yy HH:mm", // for 26 May 2000 11:25
"yyyy MMM d", // ambiguity resolved only by omitting time
"yyyymmddhh:mm:ss", // test case "200712172:2:3"
"H:m M/d/yy", // test case "9:47 5/12/2008"
"M/d/yy HH:mm:ss",
"M/d/yy HH:mm",
"M/d/yy",
// proposed rule that is unreachable due to "dd MMM yy HH:mm:ss"
// "yyyy MMM d HH:mm:ss",
// rules made unreachable by "M/d/yy HH:mm:ss" "M/d/yy HH:mm" "M/d/yy",
// (incoming digit strings do not mark themselves as y, m, or d!)
// "d/MM/yyyy HH:mm:ss", // PDFBOX-164 and PDFBOX-170
// "M/dd/yyyy hh:mm:ss",
// "MM/d/yyyy hh:mm:ss",
// "M/d/yyyy HH:mm:ss",
// "M/dd/yyyy",
// "MM/d/yyyy",
// "M/d/yyyy",
// "M/d/yyyy HH:mm:ss",
// "M/d/yy HH:mm:ss",
// subsumed by big-endian parse
// "yyyy-MM-dd'T'HH:mm:ss",
// "yyyy-MM-dd'T'HH:mm:ss",
// "yyyymmdd hh:mm:ss",
// "yyyymmdd",
// "yyyymmddX''00''", // covers 24 cases
// (orignally the above ended with '+00''00''';
// the first apostrophe quoted the plus,
// '' mapped to a single ', and the ''' was invalid)
};
/**
* Converts a Calendar to a string formatted as:
* D:yyyyMMddHHmmss#hh'mm' where # is Z, +, or -.
*
* @param cal The date to convert to a string. May be null.
* The DST_OFFSET is included when computing the output time zone.
*
* @return The date as a String to be used in a PDF document,
* or null if the cal value is null
*/
public static String toString(DateTime? cal)
{
if (cal == null)
{
return null;
}
//String offset = formatTZoffset(cal.Value.ti.get(Calendar.ZONE_OFFSET) +
//cal.get(Calendar.DST_OFFSET), "'");
//return String.format(Locale.US, "D:"
//+ "%1$4tY%1$2tm%1$2td" // yyyyMMdd
//+ "%1$2tH%1$2tM%1$2tS" // HHmmss
//+ "%2$s" // time zone
//+ "'", // trailing apostrophe
//cal, offset);
throw new NotImplementedException();
}
/**
* Converts the date to ISO 8601 string format:
* yyyy-mm-ddThh:MM:ss#hh:mm (where '#" is '+' or '-').
*
* @param cal The date to convert. Must not be null.
* The DST_OFFSET is included in the output value.
*
* @return The date represented as an ISO 8601 string.
*/
public static string toISO8601(DateTime cal)
{
//String offset = formatTZoffset(cal.get(Calendar.ZONE_OFFSET) +
//cal.get(Calendar.DST_OFFSET), ":");
//return String.format(Locale.US,
//"%1$4tY" // yyyy
//+ "-%1$2tm" // -mm (%tm adds one to cal month value)
//+ "-%1$2td" // -dd (%tm adds one to cal month value)
//+ "T" // T
//+ "%1$2tH:%1$2tM:%1$2tS" // HHmmss
//+ "%2$s", // time zone
//cal, offset);
throw new NotImplementedException();
}
/*
* Constrain a timezone offset to the range [-14:00 thru +14:00].
* by adding or subtracting multiples of a full day.
*/
private static int restrainTZoffset(long proposedOffset)
{
if (proposedOffset <= 14 * MILLIS_PER_HOUR && proposedOffset >= -14 * MILLIS_PER_HOUR)
{
// https://www.w3.org/TR/xmlschema-2/#dateTime-timezones
// Timezones between 14:00 and -14:00 are valid
return (int)proposedOffset;
}
// Constrain a timezone offset to the range [-11:59 thru +12:00].
proposedOffset = ((proposedOffset + HALF_DAY) % DAY + DAY) % DAY;
if (proposedOffset == 0)
{
return HALF_DAY;
}
// 0 <= proposedOffset < DAY
proposedOffset = (proposedOffset - HALF_DAY) % HALF_DAY;
// -HALF_DAY < proposedOffset < HALF_DAY
return (int)proposedOffset;
}
/*
* Formats a time zone offset as #hh^mm
* where # is + or -, hh is hours, ^ is a separator, and mm is minutes.
* Any separator may be specified by the second argument;
* the usual values are ":" (ISO 8601), "" (RFC 822), and "'" (PDF).
* The returned value is constrained to the range -11:59 ... 11:59.
* For offset of 0 millis, the String returned is "+00^00", never "Z".
* To get a "general" offset in form GMT#hh:mm, write
* "GMT"+DateConverter.formatTZoffset(offset, ":");
*
* Take thought in choosing the source for the millis value.
* It can come from calendarValue.getTimeZone() or from
* calendarValue.get(Calendar.ZONE_OFFSET). If a TimeZone was created
* from a valid time zone ID, then it may have a daylight savings rule.
* (As of July 4, 2013, the data base at http://www.iana.org/time-zones
* recognized 629 time zone regions. But a TimeZone created as
* new SimpleTimeZone(millisOffset, "ID"),
* will not have a daylight savings rule. (Not even if there is a
* known time zone with the given ID. To get the TimeZone named "xDT"
* with its DST rule, use an ID of EST5EDT, CST6CDT, MST7MDT, or PST8PDT.
*
* When parsing PDF dates, the incoming values DOES NOT have a TIMEZONE value.
* At most it has an OFFSET value like -04'00'. It is generally impossible to
* determine what TIMEZONE corresponds to a given OFFSET. If the date is
* in the summer when daylight savings is in effect, an offset of -0400
* might correspond to any one of the 38 regions (of 53) with standard time
* offset -0400 and no daylight saving. Or it might correspond to
* any one of the 31 regions (out of 43) that observe daylight savings
* and have standard time offset of -0500.
*
* If a Calendar has not been assigned a TimeZone with setTimeZone(),
* it will have by default the local TIMEZONE, not just the OFFSET. In the
* USA, this TimeZone will have a daylight savings rule.
*
* The offset assigned with calVal.set(Calendar.ZONE_OFFSET) differs
* from the offset in the TimeZone set by Calendar.setTimeZone(). Example:
* Suppose my local TimeZone is America/New_York. It has an offset of -05'00'.
* And suppose I set a GregorianCalendar's ZONE_OFFSET to -07'00'
* calVal = new GregorianCalendar(); // TimeZone is the local default
* calVal.set(Calendar.ZONE_OFFSET, -7* MILLIS_PER_HOUR);
* Four different offsets can be computed from calVal:
* calVal.get(Calendar.ZONE_OFFSET) => -07:00
* calVal.get(Calendar.ZONE_OFFSET) + calVal.get(Calendar.DST_OFFSET) => -06:00
* calVal.getTimeZone().getRawOffset() => -05:00
* calVal.getTimeZone().getOffset(calVal.getTimeInMillis()) => -04:00
*
* Which is correct??? I dunno, though setTimeZone() does seem to affect
* ZONE_OFFSET, and not vice versa. One cannot even test whether TimeZone
* or ZONE_OFFSET has been set; both have been set by initialization code.
* TimeZone is initialized to the local default time zone
* and ZONE_OFFSET is set from it.
*
* My choice in this DateConverter class has been to set the
* initial TimeZone of a GregorianCalendar to GMT. Thereafter
* the TimeZone is modified with {@link #adjustTimeZoneNicely}.
*
* package-private for testing
*/
private static string formatTZoffset(long millis, string sep)
{
//{
// SimpleDateFormat sdf = new SimpleDateFormat("Z"); // #hhmm
// sdf.setTimeZone(new SimpleTimeZone(restrainTZoffset(millis), "unknown"));
// String tz = sdf.format(new Date());
// return tz.substring(0, 3) + sep + tz.substring(3);
throw new NotImplementedException();
}
/*
* Parses an integer from a string, starting at and advancing a ParsePosition.
* Returns The integer that was at the given parse position, or the remedy value
* if no digits were found.
*
* The ParsePosition will be incremented by the number of digits found, but no
* more than maxlen. That is, the ParsePosition will advance across at most
* maxlen initial digits in text. The error index is ignored and unchanged.
*
* maxlen is the maximum length of the integer to parse, usually 2, but 4 for
* year fields. If the field of length maxlen begins with a digit, but contains
* a non-digit, no error is signaled and the integer value is returned.
*/
private static int parseTimeField(string text, ParsePosition where, int maxlen, int remedy)
{
if (text == null)
{
return remedy;
}
// it would seem that DecimalFormat.parse() would be simpler;
// but that class blithely ignores setMaximumIntegerDigits
int retval = 0;
int index = where.Index;
int limit = index + Math.Min(maxlen, text.Length - index);
for (; index < limit; index++)
{
// convert digit to integer
int cval = text[index] - '0';
// test to see if we got a digit
if (cval < 0 || cval > 9)
{
// no digit at index
break;
}
// append the digit to the return value
retval = retval * 10 + cval;
}
if (index == where.Index)
{
return remedy;
}
where.Index = index;
return retval;
}
/*
* Advances the ParsePosition past any and all the characters that match
* those in the optionals list. In particular, a space will skip all spaces.
*
* The start value is incremented by the number of optionals found. The error
* index is ignored and unchanged.
*
* Returns the last non-space character passed over (even if space is not in
* the optionals list.)
*/
private static char skipOptionals(string text, ParsePosition where, string optionals)
{
char retval = ' ', currch;
while (text != null && where.Index < text.Length && optionals.IndexOf((currch = text[where.Index])) >= 0)
{
retval = (currch != ' ') ? currch : retval;
where.Index++;
}
return retval;
}
/*
* If the victim string is at the given position in the text, this method
* advances the position past that string.
*
* `where` is the initial position to look at. After return, this will have
* been incremented by the length of the victim if it was found. The error
* index is ignored and unchanged.
*/
private static bool skipString(string text, string victim, ParsePosition where)
{
if (text.StartsWithOffset(victim, where.Index))
{
where.Index = where.Index + victim.Length;
return true;
}
return false;
}
/*
* Construct a new GregorianCalendar and set defaults.
* Locale is ENGLISH.
* TimeZone is "UTC" (zero offset and no DST).
* Parsing is NOT lenient. Milliseconds are zero.
*
* package-private for testing
*/
private static GregorianCalendar newGreg()
{
throw new NotImplementedException();
//GregorianCalendar retCal = new GregorianCalendar(GregorianCalendarTypes.USEnglish);
//retCal.setTimeZone(new SimpleTimeZone(0, "UTC"));
//retCal.setLenient(false);
//retCal.set(Calendar.MILLISECOND, 0);
//return retCal;
}
/*
* Install a TimeZone on a GregorianCalendar without changing the
* hours value. A plain GregorianCalendat.setTimeZone()
* adjusts the Calendar.HOUR value to compensate. This is *BAD*
* (not to say *EVIL*) when we have already set the time.
*/
private static void adjustTimeZoneNicely(GregorianCalendar cal, TimeZone tz)
{
throw new NotImplementedException();
//cal.setTimeZone(tz);
//int offset = (cal.get(Calendar.ZONE_OFFSET) + cal.get(Calendar.DST_OFFSET)) /
//MILLIS_PER_MINUTE;
//cal.add(Calendar.MINUTE, -offset);
}
/*
* Parses the end of a date string for a time zone and, if one is found,
* sets the time zone of the GregorianCalendar. Otherwise the calendar
* time zone is unchanged.
*
* The text is parsed as
* (Z|GMT|UTC)? [+- ]* h [': ]? m '?
* where the leading String is optional, h is two digits by default,
* but may be a single digit if followed by one of space, apostrophe,
* colon, or the end of string. Similarly, m is one or two digits.
* This scheme accepts the format of PDF, RFC 822, and ISO8601.
* If none of these applies (as for a time zone name), we try
* TimeZone.getTimeZone().
*
* Scanning begins at where.index. After success, the returned index
* is that of the next character after the recognized string.
*
* package-private for testing
*/
private static bool parseTZoffset(string text, GregorianCalendar cal, ParsePosition initialWhere)
{
ParsePosition where = new ParsePosition(initialWhere.Index);
//TimeZone tz = new SimpleTimeZone(0, "GMT");
//int tzHours, tzMin;
//char sign = skipOptionals(text, where, "Z+- ");
//boolean hadGMT = (sign == 'Z' || skipString(text, "GMT", where) ||
//skipString(text, "UTC", where));
//sign = (!hadGMT) ? sign : skipOptionals(text, where, "+- ");
//tzHours = parseTimeField(text, where, 2, -999);
//skipOptionals(text, where, "\': ");
//tzMin = parseTimeField(text, where, 2, 0);
//skipOptionals(text, where, "\' ");
//if (tzHours != -999)
//{
// // we parsed a time zone in default format
// int hrSign = (sign == '-' ? -1 : 1);
// tz.setRawOffset(restrainTZoffset(hrSign * (tzHours * MILLIS_PER_HOUR + tzMin *
// (long)MILLIS_PER_MINUTE)));
// updateZoneId(tz);
//}
//else if (!hadGMT)
//{
// // try to process as a name; "GMT" or "UTC" has already been processed
// String tzText = text.substring(initialWhere.getIndex()).trim();
// tz = TimeZone.getTimeZone(tzText);
// // getTimeZone returns "GMT" for unknown ids
// if ("GMT".equals(tz.getID()))
// {
// // no timezone in text, cal amd initialWhere are unchanged
// return false;
// }
// else
// {
// // we got a tz by name; use it
// where.setIndex(text.length());
// }
//}
//adjustTimeZoneNicely(cal, tz);
//initialWhere.setIndex(where.getIndex());
throw new NotImplementedException();
return true;
}
/**
* Update the zone ID based on the raw offset. This is either GMT, GMT+hh:mm or GMT-hh:mm, where
* n is between 1 and 14. The highest negative hour is -14, the highest positive hour is 12.
* Zones that don't fit in this schema are set to zone ID "unknown".
*
* @param tz the time zone to update.
*/
private static void updateZoneId(TimeZone tz)
{
//int offset = tz.getRawOffset();
//char pm = '+';
//if (offset < 0)
//{
// pm = '-';
// offset = -offset;
//}
//int hh = offset / 3600000;
//int mm = offset % 3600000 / 60000;
//if (offset == 0)
//{
// tz.setID("GMT");
//}
//else if (pm == '+' && hh <= 12)
//{
// tz.setID(String.format(Locale.US, "GMT+%02d:%02d", hh, mm));
//}
//else if (pm == '-' && hh <= 14)
//{
// tz.setID(String.format(Locale.US, "GMT-%02d:%02d", hh, mm));
//}
//else
//{
// tz.setID("unknown");
//}
throw new NotImplementedException();
}
/*
* Parses a big-endian date: year month day hour min sec.
* The year must be four digits. Other fields may be adjacent
* and delimited by length or they may follow appropriate delimiters.
* year [ -/]* month [ -/]* dayofmonth [ T]* hour [:] min [:] sec [.secFraction]
* If any numeric field is omitted, all following fields must also be omitted.
* No time zone is processed.
*
* Ambiguous dates can produce unexpected results. For example:
* 1970 12 23:08 will parse as 1970 December 23 00:08:00
*
* The parse begins at `where, on return the index
* is advanced to just beyond the last character processed.
* The error index is ignored and unchanged.
*/
private static GregorianCalendar parseBigEndianDate(String text,
ParsePosition initialWhere)
{
//ParsePosition where = new ParsePosition(initialWhere.getIndex());
//int year = parseTimeField(text, where, 4, 0);
//if (where.getIndex() != 4 + initialWhere.getIndex())
//{
// return null;
//}
//skipOptionals(text, where, "/- ");
//int month = parseTimeField(text, where, 2, 1) - 1; // Calendar months are 0...11
//skipOptionals(text, where, "/- ");
//int day = parseTimeField(text, where, 2, 1);
//skipOptionals(text, where, " T");
//int hour = parseTimeField(text, where, 2, 0);
//skipOptionals(text, where, ": ");
//int minute = parseTimeField(text, where, 2, 0);
//skipOptionals(text, where, ": ");
//int second = parseTimeField(text, where, 2, 0);
//char nextC = skipOptionals(text, where, ".");
//if (nextC == '.')
//{
// // fractions of a second: skip upto 19 digits
// parseTimeField(text, where, 19, 0);
//}
//GregorianCalendar dest = newGreg();
//try
//{
// dest.set(year, month, day, hour, minute, second);
// // trigger limit tests
// dest.getTimeInMillis();
//}
//catch (IllegalArgumentException ill)
//{
// return null;
//}
//initialWhere.setIndex(where.getIndex());
//skipOptionals(text, initialWhere, " ");
//// dest has at least a year value
//return dest;
throw new NotImplementedException();
}
/*
* See if text can be parsed as a date according to any of a list of
* formats. The time zone may be included as part of the format, or
* omitted in favor of later testing for a trailing time zone.
*
* The parse starts at `where`, upon return it will have been
* incremented to refer to the next non-space character after the date.
* If no date was found, the value is unchanged.
* The error index is ignored and unchanged.
*
* If there is a failure to find a date, or the GregorianCalendar
* for the date that was found. Unless a time zone was
* part of the format, the time zone will be GMT+0
*/
private static GregorianCalendar parseSimpleDate(string text, string[] fmts,
ParsePosition initialWhere)
{
foreach (var fmt in fmts)
{
ParsePosition where = new ParsePosition(initialWhere.Index);
//SimpleDateFormat sdf = new SimpleDateFormat(fmt, Locale.ENGLISH);
throw new NotImplementedException();
GregorianCalendar retCal = newGreg();
//sdf.setCalendar(retCal);
//if (sdf.parse(text, where) != null)
//{
// initialWhere.Index = where.Index;
// skipOptionals(text, initialWhere, " ");
// return retCal;
//}
}
return null;
}
/*
* Parses a String to see if it begins with a date, and if so,
* returns that date. The date must be strictly correct--no
* field may exceed the appropriate limit.
* (That is, the Calendar has setLenient(false).)
* Skips initial spaces, but does NOT check for "D:"
*
* The scan first tries parseBigEndianDate and parseTZoffset
* and then tries parseSimpleDate with appropriate formats,
* again followed by parseTZoffset. If at any stage the entire
* text is consumed, that date value is returned immediately.
* Otherwise the date that consumes the longest initial part
* of the text is returned.
*
* - PDF format dates are among those recognized by parseBigEndianDate.
* - The formats tried are alphaStartFormats or digitStartFormat and
* any listed in the value of moreFmts.
*/
private static DateTime? parseDate(string text, ParsePosition initialWhere)
{
if (string.IsNullOrEmpty(text))
{
return null;
}
// remember longestr date string
int longestLen = -999999;
// theorem: the above value will never be used
// proof: longestLen is only used if longestDate is not null
GregorianCalendar longestDate = null; // null says no date found yet
int whereLen; // tempcopy of where.getIndex()
ParsePosition where = new ParsePosition(initialWhere.Index);
// check for null (throws exception) and trim off surrounding spaces
skipOptionals(text, where, " ");
int startPosition = where.Index;
// try big-endian parse
GregorianCalendar retCal = parseBigEndianDate(text, where);
// check for success and a timezone
if (retCal != null && (where.Index == text.Length || parseTZoffset(text, retCal, where)))
{
// if text is fully consumed, return the date else remember it and its length
whereLen = where.Index;
if (whereLen == text.Length)
{
initialWhere.Index = whereLen;
//return retCal;
}
longestLen = whereLen;
longestDate = retCal;
}
// try one of the sets of standard formats
where.Index = startPosition;
String[] formats
= char.IsDigit(text[startPosition])
? DIGIT_START_FORMATS
: ALPHA_START_FORMATS;
retCal = parseSimpleDate(text, formats, where);
// check for success and a timezone
if (retCal != null &&
(where.Index == text.Length || parseTZoffset(text, retCal, where)))
{
// if text is fully consumed, return the date else remember it and its length
whereLen = where.Index;
if (whereLen == text.Length)
{
initialWhere.Index = whereLen;
// return retCal;
}
if (whereLen > longestLen)
{
longestLen = whereLen;
longestDate = retCal;
}
}
if (longestDate != null)
{
initialWhere.Index = longestLen;
//return longestDate;
}
throw new NotImplementedException();
//return retCal;
}
/**
* Returns the Calendar for a given COS string containing a date,
* or {@code null} if it cannot be parsed.
*
* The returned value will have 0 for DST_OFFSET.
*
* @param text A COS string containing a date.
* @return The Calendar that the text string represents, or {@code null} if it cannot be parsed.
*/
public static DateTime? toCalendar(CosString text)
{
if (text == null)
{
return null;
}
return toCalendar(text.GetString());
}
/**
* Returns the Calendar for a given string containing a date,
* or {@code null} if it cannot be parsed.
*
* The returned value will have 0 for DST_OFFSET.
*
* @param text A COS string containing a date.
* @return The Calendar that the text string represents, or {@code null} if it cannot be parsed.
*/
public static DateTime? toCalendar(string text)
{
if (text == null || text.Trim() == string.Empty)
{
return null;
}
ParsePosition where = new ParsePosition(0);
skipOptionals(text, where, " ");
skipString(text, "D:", where);
var calendar = parseDate(text, where);
if (calendar == null || where.Index != text.Length)
{
// the date string is invalid
return null;
}
return calendar;
}
}
}

2
src/UglyToad.Pdf/Util/InternalStringExtensions.cs
View File

@@ -7,8 +7,6 @@
public static string ReplaceLimited(this string value, string old, string newValue, int count)
{
throw new NotImplementedException();
return value;
}
public static bool StartsWithOffset(this string value, string start, int offset)

2
src/UglyToad.Pdf/Util/OtherEncodings.cs
View File

@@ -2,7 +2,7 @@
namespace UglyToad.Pdf.Util
{
public static class OtherEncodings
internal static class OtherEncodings
{
/// <summary>
/// Latin 1 Encoding: ISO 8859-1 is a single-byte encoding that can represent the first 256 Unicode characters.

2
src/UglyToad.Pdf/Util/ParsePosition.cs
View File

@@ -1,6 +1,6 @@
namespace UglyToad.Pdf.Util
{
public class ParsePosition
internal class ParsePosition
{
public int Index { get; set; }