lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-04-05 20:55:01 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

tidy up during investigation #600

Browse Source
This commit is contained in:
Eliot Jones 2023-05-23 19:22:00 +01:00
parent 11df5b520d
commit 20d3cc9066
2 changed files with 112 additions and 112 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/UglyToad.PdfPig/Content/Pages.cs
View File

@ -1,6 +1,5 @@
namespace UglyToad.PdfPig.Content namespace UglyToad.PdfPig.Content
{ {
using Annotations;
using Core; using Core;
using Outline; using Outline;
using System; using System;
@ -69,7 +68,8 @@
{ {
pageTreeMembers.Rotation = rotateToken.Int; pageTreeMembers.Rotation = rotateToken.Int;
} }
} }
var page = pageFactory.Create( var page = pageFactory.Create(
pageNumber, pageNumber,
pageNode.NodeDictionary, pageNode.NodeDictionary,

220
src/UglyToad.PdfPig/Graphics/Operations/TextShowing/ShowText.cs
View File

@ -1,117 +1,117 @@
namespace UglyToad.PdfPig.Graphics.Operations.TextShowing namespace UglyToad.PdfPig.Graphics.Operations.TextShowing
{ {
using System.IO; using System.IO;
using PdfPig.Core; using PdfPig.Core;
using Util.JetBrains.Annotations; using Util.JetBrains.Annotations;
/// <inheritdoc /> /// <inheritdoc />
/// <summary> /// <summary>
/// Show a text string /// Show a text string
/// </summary> /// </summary>
/// <remarks> /// <remarks>
/// <para>The input is a sequence of character codes to be shown as glyphs.</para> /// <para>The input is a sequence of character codes to be shown as glyphs.</para>
/// <para> /// <para>
/// Generally each byte represents a single character code, however starting in version 1.2+ /// Generally each byte represents a single character code, however starting in version 1.2+
/// a composite font might use multi-byte character codes to map to glyphs. /// a composite font might use multi-byte character codes to map to glyphs.
/// For these composite fonts, the <see cref="T:UglyToad.PdfPig.Fonts.Cmap.CMap" /> of the font defines the mapping from code to glyph. /// For these composite fonts, the <see cref="T:UglyToad.PdfPig.Fonts.Cmap.CMap" /> of the font defines the mapping from code to glyph.
/// </para> /// </para>
/// <para> /// <para>
/// The grouping of character codes in arguments to this operator does not have any impact on the meaning; for example:<br /> /// The grouping of character codes in arguments to this operator does not have any impact on the meaning; for example:<br />
/// (Abc) Tj is equivalent to (A) Tj (b) Tj (c) Tj<br /> /// (Abc) Tj is equivalent to (A) Tj (b) Tj (c) Tj<br />
/// However grouping character codes makes the document easier to search and extract text from. /// However grouping character codes makes the document easier to search and extract text from.
/// </para> /// </para>
/// </remarks> /// </remarks>
public class ShowText : IGraphicsStateOperation public class ShowText : IGraphicsStateOperation
{ {
/// <summary> /// <summary>
/// The symbol for this operation in a stream. /// The symbol for this operation in a stream.
/// </summary> /// </summary>
public const string Symbol = "Tj"; public const string Symbol = "Tj";
/// <inheritdoc /> /// <inheritdoc />
public string Operator => Symbol; public string Operator => Symbol;
/// <summary> /// <summary>
/// The text string to show. /// The text string to show.
/// </summary> /// </summary>
[CanBeNull] [CanBeNull]
public string Text { get; } public string Text { get; }
/// <summary> /// <summary>
/// The bytes of the string to show. /// The bytes of the string to show.
/// </summary> /// </summary>
[CanBeNull] [CanBeNull]
public byte[] Bytes { get; } public byte[] Bytes { get; }
/// <summary> /// <summary>
/// Create a new <see cref="ShowText"/>. /// Create a new <see cref="ShowText"/>.
/// </summary> /// </summary>
public ShowText(string text) public ShowText(string text)
{
Text = text;
}
/// <summary>
/// Create a new <see cref="ShowText"/>.
/// </summary>
public ShowText(byte[] hexBytes)
{
Bytes = hexBytes;
}
/// <inheritdoc />
public void Run(IOperationContext operationContext)
{
var input = new ByteArrayInputBytes(Text != null ? OtherEncodings.StringAsLatin1Bytes(Text) : Bytes);
operationContext.ShowText(input);
}
string EscapeText(string text)
{ {
if (text is null) return null; Text = text;
// Fix Issue 350 from PDF Spec 1.7 (page 408) on handling 'special characters' of '(', ')' and '\'. }
// The strings must conform to the syntax for string objects. /// <summary>
/// Create a new <see cref="ShowText"/>.
/// </summary>
public ShowText(byte[] hexBytes)
{
Bytes = hexBytes;
}
/// <inheritdoc />
public void Run(IOperationContext operationContext)
{
var input = new ByteArrayInputBytes(Text != null ? OtherEncodings.StringAsLatin1Bytes(Text) : Bytes);
operationContext.ShowText(input);
}
string EscapeText(string text)
{
if (text is null) return null;
// Fix Issue 350 from PDF Spec 1.7 (page 408) on handling 'special characters' of '(', ')' and '\'.
// The strings must conform to the syntax for string objects.
// When a string is written by enclosing the data in parentheses, // When a string is written by enclosing the data in parentheses,
// bytes whose values are the same as those // bytes whose values are the same as those
// of the ASCII characters left parenthesis (40), right parenthesis (41), and backslash (92) // of the ASCII characters left parenthesis (40), right parenthesis (41), and backslash (92)
// must be preceded by a backslash character. // must be preceded by a backslash character.
// All other byte values between 0 and 255 may be used in a string object. // All other byte values between 0 and 255 may be used in a string object.
// These rules apply to each individual byte in a string object, whether the string is interpreted by the text-showing operators // These rules apply to each individual byte in a string object, whether the string is interpreted by the text-showing operators
// as single-byte or multiple-byte character codes. // as single-byte or multiple-byte character codes.
// Note: order of replacing is important. Replace slash first before brackets. // Note: order of replacing is important. Replace slash first before brackets.
text = text.Replace(@"\", @"\\)"); // Escape any slash '\' -> '\\' text = text.Replace(@"\", @"\\)"); // Escape any slash '\' -> '\\'
text = text.Replace("(", @"\("); // Escape any open brackets '(' -> '\(' text = text.Replace("(", @"\("); // Escape any open brackets '(' -> '\('
text = text.Replace(")", @"\)"); // Escape any close brackets ')' -> '\)' text = text.Replace(")", @"\)"); // Escape any close brackets ')' -> '\)'
return text; return text;
} }
/// <inheritdoc /> /// <inheritdoc />
public void Write(Stream stream) public void Write(Stream stream)
{ {
if (Bytes != null) if (Bytes != null)
{ {
stream.WriteHex(Bytes); stream.WriteHex(Bytes);
} }
else else
{ {
var EscapedText = EscapeText(Text); // escape '(', ')' or '\' var escapedText = EscapeText(Text); // escape '(', ')' or '\'
stream.WriteText($"({EscapedText})"); stream.WriteText($"({escapedText})");
} }
stream.WriteWhiteSpace(); stream.WriteWhiteSpace();
stream.WriteText(Symbol); stream.WriteText(Symbol);
stream.WriteNewLine(); stream.WriteNewLine();
} }
/// <inheritdoc /> /// <inheritdoc />
public override string ToString() public override string ToString()
{ {
return $"{Text} {Symbol}"; return $"{Text} {Symbol}";
} }
} }
} }