starred/markdig
1
0
Fork 0
mirror of https://github.com/xoofx/markdig.git synced 2026-10-08 06:38:39 +00:00
Code Issues 690 Packages Projects Releases 21 Wiki Activity

Move helper classes to Helpers namespace. Regroup methods in helpers

Browse Source
This commit is contained in:
Alexandre Mutel
2016-02-19 05:53:48 +09:00
parent 96de9ec7cc
commit 2fe75c6af2
21 changed files with 232 additions and 538 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/Textamina.Markdig/Formatters/HtmlFormatter.cs
View File

@@ -2,6 +2,7 @@
using System.Collections.Generic;
using System.Globalization;
using System.IO;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Syntax;
namespace Textamina.Markdig.Formatters

1
src/Textamina.Markdig/Formatters/HtmlTextWriter.cs
View File

@@ -1,4 +1,5 @@
using System.IO;
using Textamina.Markdig.Helpers;
namespace Textamina.Markdig.Formatters
{

461
src/Textamina.Markdig/Formatters/Scanner.cs
View File

@@ -1,461 +0,0 @@
using System;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Formatters
{
/// <summary>
/// Contains the regular expressions that are used in the parsers.
/// </summary>
internal static partial class Scanner
{
/// <summary>
/// List of valid schemes of an URL. The array must be sorted.
/// </summary>
private static readonly string[] schemeArray = new[]
{
"AAA", "AAAS", "ABOUT", "ACAP", "ADIUMXTRA", "AFP", "AFS", "AIM", "APT", "ATTACHMENT", "AW", "BESHARE",
"BITCOIN", "BOLO", "CALLTO", "CAP", "CHROME", "CHROME-EXTENSION", "CID", "COAP", "COM-EVENTBRITE-ATTENDEE",
"CONTENT", "CRID", "CVS", "DATA", "DAV", "DICT", "DLNA-PLAYCONTAINER", "DLNA-PLAYSINGLE", "DNS", "DOI",
"DTN", "DVB", "ED2K", "FACETIME", "FEED", "FILE", "FINGER", "FISH", "FTP", "GEO", "GG", "GIT",
"GIZMOPROJECT", "GO", "GOPHER", "GTALK", "H323", "HCP", "HTTP", "HTTPS", "IAX", "ICAP", "ICON", "IM", "IMAP",
"INFO", "IPN", "IPP", "IRC", "IRC6", "IRCS", "IRIS", "IRIS.BEEP", "IRIS.LWZ", "IRIS.XPC", "IRIS.XPCS",
"ITMS", "JAR", "JAVASCRIPT", "JMS", "KEYPARC", "LASTFM", "LDAP", "LDAPS", "MAGNET", "MAILTO", "MAPS",
"MARKET", "MESSAGE", "MID", "MMS", "MS-HELP", "MSNIM", "MSRP", "MSRPS", "MTQP", "MUMBLE", "MUPDATE", "MVN",
"NEWS", "NFS", "NI", "NIH", "NNTP", "NOTES", "OID", "OPAQUELOCKTOKEN", "PALM", "PAPARAZZI", "PLATFORM",
"POP", "PRES", "PROXY", "PSYC", "QUERY", "RES", "RESOURCE", "RMI", "RSYNC", "RTMP", "RTSP", "SECONDLIFE",
"SERVICE", "SESSION", "SFTP", "SGN", "SHTTP", "SIEVE", "SIP", "SIPS", "SKYPE", "SMB", "SMS", "SNMP",
"SOAP.BEEP", "SOAP.BEEPS", "SOLDAT", "SPOTIFY", "SSH", "STEAM", "SVN", "TAG", "TEAMSPEAK", "TEL", "TELNET",
"TFTP", "THINGS", "THISMESSAGE", "TIP", "TN3270", "TV", "UDP", "UNREAL", "URN", "UT2004", "VEMMI",
"VENTRILO", "VIEW-SOURCE", "WEBCAL", "WS", "WSS", "WTAI", "WYCIWYG", "XCON", "XCON-USERID", "XFIRE",
"XMLRPC.BEEP", "XMLRPC.BEEPS", "XMPP", "XRI", "YMSGR", "Z39.50R", "Z39.50S"
};
/// <summary>
/// Try to match URI autolink after first &lt;, returning number of chars matched.
/// </summary>
public static int scan_autolink_uri(string s, int pos, int sourceLength)
{
/*!re2c
scheme [:]([^\x00-\x20<>\\]|escaped_char)*[>] { return (p - start); }
.? { return 0; }
*/
// for now the tests do not include anything that would require the use of `escaped_char` part so it is ignored.
// 24 is the maximum length of a valid scheme
var checkLen = sourceLength - pos;
if (checkLen > 24)
checkLen = 24;
// PERF: potential small improvement - instead of using IndexOf, check char-by-char and return as soon as an invalid character is found ([^a-z0-9\.])
// alternative approach (if we want to go crazy about performance - store the valid schemes as a prefix tree and lookup the valid scheme char by char and
// return as soon as the part does not match any prefix.
var colonpos = s.IndexOf(':', pos, checkLen);
if (colonpos == -1)
return 0;
var potentialScheme = s.Substring(pos, colonpos - pos).ToUpperInvariant();
if (Array.BinarySearch(schemeArray, potentialScheme, StringComparer.Ordinal) < 0)
return 0;
for (var i = colonpos + 1; i < sourceLength; i++)
{
var c = s[i];
if (c == '>')
return i - pos + 1;
if (c == '<' || c <= 0x20)
return 0;
}
return 0;
}
/// <summary>
/// Try to match a link title (in single quotes, in double quotes, or
/// in parentheses), returning number of chars matched. Allow one
/// level of internal nesting (quotes within quotes).
/// </summary>
public static int scan_link_title(string s, int pos, int sourceLength)
{
/*!re2c
["] (escaped_char|[^"\x00])* ["] { return (p - start); }
['] (escaped_char|[^'\x00])* ['] { return (p - start); }
[(] (escaped_char|[^)\x00])* [)] { return (p - start); }
.? { return 0; }
*/
if (pos + 2 >= sourceLength)
return 0;
var c1 = s[pos];
if (c1 != '"' && c1 != '\'' && c1 != '(')
return 0;
if (c1 == '(') c1 = ')';
var nextEscaped = false;
for (var i = pos + 1; i < sourceLength; i++)
{
var c = s[i];
if (c == c1 && !nextEscaped)
return i - pos + 1;
nextEscaped = !nextEscaped && c == '\\';
}
return 0;
}
/// <summary>
/// Match space characters, including newlines.
/// </summary>
public static int scan_spacechars(string s, int pos, int sourceLength)
{
/*!re2c
[ \t\n]* { return (p - start); }
. { return 0; }
*/
if (pos >= sourceLength)
return 0;
for (var i = pos; i < sourceLength; i++)
{
if (!Utility.IsWhitespace(s[i]))
return i - pos;
}
return sourceLength - pos;
}
/// <summary>
/// Match ATX heading start.
/// </summary>
public static int scan_atx_heading_start(string s, int pos, int sourceLength, out int headingLevel)
{
/*!re2c
[#]{1,6} ([ ]+|[\n]) { return (p - start); }
.? { return 0; }
*/
headingLevel = 1;
if (pos + 1 >= sourceLength)
return 0;
if (s[pos] != '#')
return 0;
var spaceExists = false;
for (var i = pos + 1; i < sourceLength; i++)
{
var c = s[i];
if (c == '#')
{
if (headingLevel == 6)
return 0;
if (spaceExists)
return i - pos;
else
headingLevel++;
}
else if (c == ' ')
{
spaceExists = true;
}
else if (c == '\n')
{
return i - pos + 1;
}
else
{
return spaceExists ? i - pos : 0;
}
}
if (spaceExists)
return sourceLength - pos;
return 0;
}
/// <summary>
/// Match sexext heading line. Return 1 for level-1 heading,
/// 2 for level-2, 0 for no match.
/// </summary>
public static int scan_setext_heading_line(string s, int pos, int sourceLength)
{
/*!re2c
[=]+ [ ]* [\n] { return 1; }
[-]+ [ ]* [\n] { return 2; }
.? { return 0; }
*/
if (pos >= sourceLength)
return 0;
var c1 = s[pos];
if (c1 != '=' && c1 != '-')
return 0;
var fin = false;
for (var i = pos + 1; i < sourceLength; i++)
{
var c = s[i];
if (c == c1 && !fin)
continue;
fin = true;
if (c == ' ')
continue;
if (c == '\n')
break;
return 0;
}
return c1 == '=' ? 1 : 2;
}
/// <summary>
/// Scan a thematic break line: "...three or more hyphens, asterisks,
/// or underscores on a line by themselves. If you wish, you may use
/// spaces between the hyphens or asterisks."
/// </summary>
public static int scan_thematic_break(string s, int pos, int sourceLength)
{
// @"^([\*][ ]*){3,}[\s]*$",
// @"^([_][ ]*){3,}[\s]*$",
// @"^([-][ ]*){3,}[\s]*$",
var count = 0;
var x = '\0';
var ipos = pos;
while (ipos < sourceLength)
{
var c = s[ipos++];
if (c == ' ' || c == '\n')
continue;
if (count == 0)
{
if (c == '*' || c == '_' || c == '-')
x = c;
else
return 0;
count = 1;
}
else if (c == x)
count++;
else
return 0;
}
if (count < 3)
return 0;
return sourceLength - pos;
}
/// <summary>
/// Scan an opening code fence. Returns the number of characters forming the fence.
/// </summary>
public static int scan_open_code_fence(string s, int pos, int sourceLength)
{
/*!re2c
[`]{3,} / [^`\n\x00]*[\n] { return (p - start); }
[~]{3,} / [^~\n\x00]*[\n] { return (p - start); }
.? { return 0; }
*/
if (pos + 3 >= sourceLength)
return 0;
var fchar = s[pos];
if (fchar != '`' && fchar != '~')
return 0;
var cnt = 1;
var fenceDone = false;
for (var i = pos + 1; i < sourceLength; i++)
{
var c = s[i];
if (c == fchar)
{
if (fenceDone)
return 0;
cnt++;
continue;
}
fenceDone = true;
if (cnt < 3)
return 0;
if (c == '\n')
return cnt;
}
if (cnt < 3)
return 0;
return cnt;
}
/// <summary>
/// Scan a closing code fence with length at least len.
/// </summary>
public static int scan_close_code_fence(string s, int pos, int len, int sourceLength)
{
/*!re2c
([`]{3,} | [~]{3,}) / spacechar* [\n]
{ if (p - start > len) {
return (p - start);
} else {
return 0;
} }
.? { return 0; }
*/
if (pos + len >= sourceLength)
return 0;
var c1 = s[pos];
if (c1 != '`' && c1 != '~')
return 0;
var cnt = 1;
var spaces = false;
for (var i = pos + 1; i < sourceLength; i++)
{
var c = s[i];
if (c == c1 && !spaces)
cnt++;
else if (c == ' ')
spaces = true;
else if (c == '\n')
return cnt < len ? 0 : cnt;
else
return 0;
}
return 0;
}
/// <summary>
/// Scans an entity.
/// Returns number of chars matched.
/// </summary>
public static int scan_entity(string s, int pos, int length, out string namedEntity, out int numericEntity)
{
/*!re2c
[&] ([#] ([Xx][A-Fa-f0-9]{1,8}|[0-9]{1,8}) |[A-Za-z][A-Za-z0-9]{1,31} ) [;]
{ return (p - start); }
.? { return 0; }
*/
var lastPos = pos + length;
namedEntity = null;
numericEntity = 0;
if (pos + 3 >= lastPos)
return 0;
if (s[pos] != '&')
return 0;
char c;
int i;
int counter = 0;
if (s[pos + 1] == '#')
{
c = s[pos + 2];
if (c == 'x' || c == 'X')
{
// expect 1-8 hex digits starting from pos+3
for (i = pos + 3; i < lastPos; i++)
{
c = s[i];
if (c >= '0' && c <= '9')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*16 + (c - '0');
continue;
}
else if (c >= 'A' && c <= 'F')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*16 + (c - 'A' + 10);
continue;
}
else if (c >= 'a' && c <= 'f')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*16 + (c - 'a' + 10);
continue;
}
if (c == ';')
return counter == 0 ? 0 : i - pos + 1;
return 0;
}
}
else
{
// expect 1-8 digits starting from pos+2
for (i = pos + 2; i < lastPos; i++)
{
c = s[i];
if (c >= '0' && c <= '9')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*10 + (c - '0');
continue;
}
if (c == ';')
return counter == 0 ? 0 : i - pos + 1;
return 0;
}
}
}
else
{
// expect a letter and 1-31 letters or digits
c = s[pos + 1];
if ((c < 'A' || c > 'Z') && (c < 'a' && c > 'z'))
return 0;
for (i = pos + 2; i < lastPos; i++)
{
c = s[i];
if ((c >= '0' && c <= '9') || (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'))
{
if (++counter == 32)
return 0;
continue;
}
if (c == ';')
{
namedEntity = s.Substring(pos + 1, counter + 1);
return counter == 0 ? 0 : i - pos + 1;
}
return 0;
}
}
return 0;
}
}
}

32
src/Textamina.Markdig/Utility.cs → src/Textamina.Markdig/Helpers/CharHelper.cs
View File

@@ -1,11 +1,11 @@
using System.Runtime.CompilerServices;
namespace Textamina.Markdig.Parsing
namespace Textamina.Markdig.Helpers
{
internal class Utility
public static class CharHelper
{
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsWhitespace(char c)
public static bool IsWhitespace(this char c)
{
// 2.1 Characters and lines
// A whitespace character is a space(U + 0020), tab(U + 0009), newline(U + 000A), line tabulation (U + 000B), form feed (U + 000C), or carriage return (U + 000D).
@@ -13,38 +13,38 @@ namespace Textamina.Markdig.Parsing
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsControl(char c)
public static bool IsControl(this char c)
{
return c < ' ' || char.IsControl(c);
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsEscapableSymbol(char c)
public static bool IsEscapableSymbol(this char c)
{
// char.IsSymbol also works with Unicode symbols that cannot be escaped based on the specification.
return (c > ' ' && c < '0') || (c > '9' && c < 'A') || (c > 'Z' && c < 'a') || (c > 'z' && c < 127) || c == '•';
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsWhiteSpaceOrZero(char c)
public static bool IsWhiteSpaceOrZero(this char c)
{
return IsWhitespace(c) || IsZero(c);
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsNewLine(char c)
public static bool IsNewLine(this char c)
{
return c == '\n';
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsZero(char c)
public static bool IsZero(this char c)
{
return c == '\0';
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsSpace(char c)
public static bool IsSpace(this char c)
{
// 2.1 Characters and lines
// A space is U+0020.
@@ -52,7 +52,7 @@ namespace Textamina.Markdig.Parsing
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsTab(char c)
public static bool IsTab(this char c)
{
// 2.1 Characters and lines
// A space is U+0009.
@@ -60,13 +60,13 @@ namespace Textamina.Markdig.Parsing
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsSpaceOrTab(char c)
public static bool IsSpaceOrTab(this char c)
{
return IsSpace(c) || IsTab(c);
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static char EscapeInsecure(char c)
public static char EscapeInsecure(this char c)
{
// 2.3 Insecure characters
// For security reasons, the Unicode character U+0000 must be replaced with the REPLACEMENT CHARACTER (U+FFFD).
@@ -74,24 +74,24 @@ namespace Textamina.Markdig.Parsing
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsBulletListMarker(char c)
public static bool IsBulletListMarker(this char c)
{
return c == '-' || c == '+' || c == '*';
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsAlphaUpper(char c)
public static bool IsAlphaUpper(this char c)
{
return c >= 'A' && c <= 'Z';
}
[MethodImpl(MethodImplOptionPortable.AggressiveInlining)]
public static bool IsAlphaNumeric(char c)
public static bool IsAlphaNumeric(this char c)
{
return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') || (c >= '0' && c <= '9');
}
public static bool IsASCIIPunctuation(char c)
public static bool IsAsciiPunctuation(this char c)
{
// 2.1 Characters and lines
// An ASCII punctuation character is !, ", #, $, %, &, ', (, ), *, +, ,, -, ., /, :, ;, <, =, >, ?, @, [, \, ], ^, _, `, {, |, }, or ~.

4
src/Textamina.Markdig/Formatters/EntityDecoder.cs → src/Textamina.Markdig/Helpers/EntityHelper.cs
View File

@@ -1,9 +1,9 @@
using System;
using System.Collections.Generic;
namespace Textamina.Markdig.Formatters
namespace Textamina.Markdig.Helpers
{
internal static class EntityDecoder
public static class EntityHelper
{
/// <summary>
/// Decodes the given HTML entity to the matching Unicode characters.

161
src/Textamina.Markdig/Formatters/HtmlHelper.cs → src/Textamina.Markdig/Helpers/HtmlHelper.cs
View File

@@ -1,8 +1,8 @@
using System;
using System.Text;
using Textamina.Markdig.Parsing;
using Textamina.Markdig.Formatters;
namespace Textamina.Markdig.Formatters
namespace Textamina.Markdig.Helpers
{
internal static class HtmlHelper
{
@@ -31,8 +31,29 @@ namespace Textamina.Markdig.Formatters
true, true, true, true, true, true, true, true, true, true, true, false, false, false, false, false
};
[ThreadStatic]
private static readonly StringBuilder TempBuilder = new StringBuilder();
/// <summary>
/// List of valid schemes of an URL. The array must be sorted.
/// </summary>
private static readonly string[] SchemeArray = new[]
{
"AAA", "AAAS", "ABOUT", "ACAP", "ADIUMXTRA", "AFP", "AFS", "AIM", "APT", "ATTACHMENT", "AW", "BESHARE",
"BITCOIN", "BOLO", "CALLTO", "CAP", "CHROME", "CHROME-EXTENSION", "CID", "COAP", "COM-EVENTBRITE-ATTENDEE",
"CONTENT", "CRID", "CVS", "DATA", "DAV", "DICT", "DLNA-PLAYCONTAINER", "DLNA-PLAYSINGLE", "DNS", "DOI",
"DTN", "DVB", "ED2K", "FACETIME", "FEED", "FILE", "FINGER", "FISH", "FTP", "GEO", "GG", "GIT",
"GIZMOPROJECT", "GO", "GOPHER", "GTALK", "H323", "HCP", "HTTP", "HTTPS", "IAX", "ICAP", "ICON", "IM", "IMAP",
"INFO", "IPN", "IPP", "IRC", "IRC6", "IRCS", "IRIS", "IRIS.BEEP", "IRIS.LWZ", "IRIS.XPC", "IRIS.XPCS",
"ITMS", "JAR", "JAVASCRIPT", "JMS", "KEYPARC", "LASTFM", "LDAP", "LDAPS", "MAGNET", "MAILTO", "MAPS",
"MARKET", "MESSAGE", "MID", "MMS", "MS-HELP", "MSNIM", "MSRP", "MSRPS", "MTQP", "MUMBLE", "MUPDATE", "MVN",
"NEWS", "NFS", "NI", "NIH", "NNTP", "NOTES", "OID", "OPAQUELOCKTOKEN", "PALM", "PAPARAZZI", "PLATFORM",
"POP", "PRES", "PROXY", "PSYC", "QUERY", "RES", "RESOURCE", "RMI", "RSYNC", "RTMP", "RTSP", "SECONDLIFE",
"SERVICE", "SESSION", "SFTP", "SGN", "SHTTP", "SIEVE", "SIP", "SIPS", "SKYPE", "SMB", "SMS", "SNMP",
"SOAP.BEEP", "SOAP.BEEPS", "SOLDAT", "SPOTIFY", "SSH", "STEAM", "SVN", "TAG", "TEAMSPEAK", "TEL", "TELNET",
"TFTP", "THINGS", "THISMESSAGE", "TIP", "TN3270", "TV", "UDP", "UNREAL", "URN", "UT2004", "VEMMI",
"VENTRILO", "VIEW-SOURCE", "WEBCAL", "WS", "WSS", "WTAI", "WYCIWYG", "XCON", "XCON-USERID", "XFIRE",
"XMLRPC.BEEP", "XMLRPC.BEEPS", "XMPP", "XRI", "YMSGR", "Z39.50R", "Z39.50S"
};
[ThreadStatic] private static readonly StringBuilder TempBuilder = new StringBuilder();
/// <summary>
/// Destructively unescape a string: remove backslashes before punctuation or symbol characters.
@@ -45,7 +66,7 @@ namespace Textamina.Markdig.Formatters
int lastPos = 0;
int match;
char c;
char[] search = new[] { '\\', '&' };
char[] search = new[] {'\\', '&'};
var sb = TempBuilder;
sb.Clear();
@@ -60,7 +81,7 @@ namespace Textamina.Markdig.Formatters
break;
c = url[searchPos];
if (Utility.IsEscapableSymbol(c))
if (CharHelper.IsEscapableSymbol(c))
{
sb.Append(url, lastPos, searchPos - lastPos - 1);
lastPos = searchPos;
@@ -70,7 +91,8 @@ namespace Textamina.Markdig.Formatters
{
string namedEntity;
int numericEntity;
match = Scanner.scan_entity(url, searchPos, url.Length - searchPos, out namedEntity, out numericEntity);
match = scan_entity(url, searchPos, url.Length - searchPos, out namedEntity,
out numericEntity);
if (match == 0)
{
searchPos++;
@@ -81,7 +103,7 @@ namespace Textamina.Markdig.Formatters
if (namedEntity != null)
{
var decoded = EntityDecoder.DecodeEntity(namedEntity);
var decoded = EntityHelper.DecodeEntity(namedEntity);
if (decoded != null)
{
sb.Append(url, lastPos, searchPos - match - lastPos);
@@ -91,7 +113,7 @@ namespace Textamina.Markdig.Formatters
}
else if (numericEntity > 0)
{
var decoded = EntityDecoder.DecodeEntity(numericEntity);
var decoded = EntityHelper.DecodeEntity(numericEntity);
if (decoded != null)
{
sb.Append(url, lastPos, searchPos - match - lastPos);
@@ -122,7 +144,7 @@ namespace Textamina.Markdig.Formatters
/// Escapes special URL characters.
/// </summary>
/// <remarks>Orig: escape_html(inp, preserve_entities)</remarks>
internal static void EscapeUrl(string input, HtmlTextWriter target)
public static void EscapeUrl(string input, HtmlTextWriter target)
{
if (input == null)
return;
@@ -188,7 +210,7 @@ namespace Textamina.Markdig.Formatters
/// Escapes special HTML characters.
/// </summary>
/// <remarks>Orig: escape_html(inp, preserve_entities)</remarks>
internal static void EscapeHtml(string input, HtmlTextWriter target)
public static void EscapeHtml(string input, HtmlTextWriter target)
{
if (input.Length == 0)
return;
@@ -230,6 +252,7 @@ namespace Textamina.Markdig.Formatters
target.Write(buffer, lastPos, input.Length - lastPos);
}
/*
/// <summary>
@@ -282,5 +305,121 @@ namespace Textamina.Markdig.Formatters
}
}
*/
/// <summary>
/// Scans an entity.
/// Returns number of chars matched.
/// </summary>
public static int scan_entity(string s, int pos, int length, out string namedEntity, out int numericEntity)
{
/*!re2c
[&] ([#] ([Xx][A-Fa-f0-9]{1,8}|[0-9]{1,8}) |[A-Za-z][A-Za-z0-9]{1,31} ) [;]
{ return (p - start); }
.? { return 0; }
*/
var lastPos = pos + length;
namedEntity = null;
numericEntity = 0;
if (pos + 3 >= lastPos)
return 0;
if (s[pos] != '&')
return 0;
char c;
int i;
int counter = 0;
if (s[pos + 1] == '#')
{
c = s[pos + 2];
if (c == 'x' || c == 'X')
{
// expect 1-8 hex digits starting from pos+3
for (i = pos + 3; i < lastPos; i++)
{
c = s[i];
if (c >= '0' && c <= '9')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*16 + (c - '0');
continue;
}
else if (c >= 'A' && c <= 'F')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*16 + (c - 'A' + 10);
continue;
}
else if (c >= 'a' && c <= 'f')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*16 + (c - 'a' + 10);
continue;
}
if (c == ';')
return counter == 0 ? 0 : i - pos + 1;
return 0;
}
}
else
{
// expect 1-8 digits starting from pos+2
for (i = pos + 2; i < lastPos; i++)
{
c = s[i];
if (c >= '0' && c <= '9')
{
if (++counter == 9) return 0;
numericEntity = numericEntity*10 + (c - '0');
continue;
}
if (c == ';')
return counter == 0 ? 0 : i - pos + 1;
return 0;
}
}
}
else
{
// expect a letter and 1-31 letters or digits
c = s[pos + 1];
if ((c < 'A' || c > 'Z') && (c < 'a' && c > 'z'))
return 0;
for (i = pos + 2; i < lastPos; i++)
{
c = s[i];
if ((c >= '0' && c <= '9') || (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'))
{
if (++counter == 32)
return 0;
continue;
}
if (c == ';')
{
namedEntity = s.Substring(pos + 1, counter + 1);
return counter == 0 ? 0 : i - pos + 1;
}
return 0;
}
}
return 0;
}
public static bool IsUrlScheme(string scheme)
{
return Array.BinarySearch(SchemeArray, scheme, StringComparer.Ordinal) >= 0;
}
}
}

3
src/Textamina.Markdig/Parsing/MarkdownParser.cs
View File

@@ -3,6 +3,7 @@ using System.Collections.Generic;
using System.IO;
using System.Text;
using System.Xml.Serialization;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Syntax;
namespace Textamina.Markdig.Parsing
@@ -381,7 +382,7 @@ namespace Textamina.Markdig.Parsing
var c = (char) nextChar;
// 2.3 Insecure characters
c = Utility.EscapeInsecure(c);
c = CharHelper.EscapeInsecure(c);
// Go to next char, expecting most likely a \n, otherwise skip it
// TODO: Should we treat it as an error in no \n is following?

5
src/Textamina.Markdig/Syntax/BreakBlock.cs
View File

@@ -1,4 +1,5 @@
using Textamina.Markdig.Parsing;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
{
@@ -38,7 +39,7 @@ namespace Textamina.Markdig.Syntax
{
count++;
}
else if (!Utility.IsSpace(c) || count == 0)
else if (!CharHelper.IsSpace(c) || count == 0)
{
return MatchLineResult.None;
}

5
src/Textamina.Markdig/Syntax/CodeBlock.cs
View File

@@ -1,4 +1,5 @@
using System;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -33,8 +34,8 @@ namespace Textamina.Markdig.Syntax
// 4.4 Indented code blocks
var c = liner.Current;
var isTab = Utility.IsTab(c);
var isSpace = Utility.IsSpace(c);
var isTab = CharHelper.IsTab(c);
var isSpace = CharHelper.IsSpace(c);
if ((isTab || (isSpace && (liner.Start - position) == 3)) && !liner.IsBlankLine())
{
liner.NextChar();

9
src/Textamina.Markdig/Syntax/HeadingBlock.cs
View File

@@ -1,4 +1,5 @@
using Textamina.Markdig.Parsing;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
{
@@ -44,7 +45,7 @@ namespace Textamina.Markdig.Syntax
// closing # will be handled later, because anyway we have matched
// A space is required after leading #
if (leadingCount > 0 && leadingCount <=6 && (Utility.IsSpace(c) || liner.IsEol))
if (leadingCount > 0 && leadingCount <=6 && (CharHelper.IsSpace(c) || liner.IsEol))
{
liner.NextChar();
state.Block = new HeadingBlock() {Level = leadingCount};
@@ -58,7 +59,7 @@ namespace Textamina.Markdig.Syntax
c = liner[i];
if (endState == 0)
{
if (Utility.IsSpace(c)) // TODO: Not clear if it is a space or space+tab in the specs
if (CharHelper.IsSpace(c)) // TODO: Not clear if it is a space or space+tab in the specs
{
continue;
}
@@ -74,7 +75,7 @@ namespace Textamina.Markdig.Syntax
if (countClosingTags > 0)
{
if (Utility.IsSpace(c))
if (CharHelper.IsSpace(c))
{
liner.End = i - 1;
}

9
src/Textamina.Markdig/Syntax/HtmlBlock.cs
View File

@@ -1,4 +1,5 @@
using System;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -107,7 +108,7 @@ namespace Textamina.Markdig.Syntax
for (int i = 0; i < 3; i++)
{
if (!Utility.IsSpace(liner.PeekChar(index)))
if (!CharHelper.IsSpace(liner.PeekChar(index)))
{
break;
}
@@ -129,7 +130,7 @@ namespace Textamina.Markdig.Syntax
{
return CreateHtmlBlock(ref state, HtmlBlockType.Comment); // group 2
}
if (Utility.IsAlphaUpper(c))
if (CharHelper.IsAlphaUpper(c))
{
return CreateHtmlBlock(ref state, HtmlBlockType.DocumentType); // group 4
}
@@ -157,14 +158,14 @@ namespace Textamina.Markdig.Syntax
for (; count < tag.Length; index++, count++)
{
c = liner.PeekChar(index);
if (!Utility.IsAlphaNumeric(c))
if (!CharHelper.IsAlphaNumeric(c))
{
break;
}
tag[count] = char.ToLowerInvariant(c);
}
if (!(c == '>' || (!hasLeadingClose && c == '/' && liner.PeekChar(index + 1) == '>') || Utility.IsWhitespace(c) || c == '\0'))
if (!(c == '>' || (!hasLeadingClose && c == '/' && liner.PeekChar(index + 1) == '>') || CharHelper.IsWhitespace(c) || c == '\0'))
{
return MatchLineResult.None;
}

7
src/Textamina.Markdig/Syntax/Inlines/CodeInline.cs
View File

@@ -1,3 +1,4 @@
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -33,8 +34,8 @@ namespace Textamina.Markdig.Syntax
while (c != '\0')
{
// Skip new lines
var isWhitespace = Utility.IsWhitespace(c);
if (!(Utility.IsNewLine(c) || (builder.Length == 0 && isWhitespace) || (lastWhiteSpace && isWhitespace)))
var isWhitespace = CharHelper.IsWhitespace(c);
if (!(CharHelper.IsNewLine(c) || (builder.Length == 0 && isWhitespace) || (lastWhiteSpace && isWhitespace)))
{
if (c == '`')
{
@@ -62,7 +63,7 @@ namespace Textamina.Markdig.Syntax
int newLength = builder.Length;
for (int i = builder.Length - 1; i >= 0; i--)
{
if (Utility.IsWhitespace(builder[i]))
if (CharHelper.IsWhitespace(builder[i]))
{
newLength--;
}

17
src/Textamina.Markdig/Syntax/Inlines/EmphasisInline.cs
View File

@@ -1,4 +1,5 @@
using System;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -41,11 +42,11 @@ namespace Textamina.Markdig.Syntax
// (b) either not followed by a punctuation character, or preceded by Unicode whitespace
// or a punctuation character.
// For purposes of this definition, the beginning and the end of the line count as Unicode whitespace.
var afterIsPunctuation = Utility.IsASCIIPunctuation(c);
bool canOpen = !Utility.IsWhiteSpaceOrZero(c) &&
var afterIsPunctuation = CharHelper.IsAsciiPunctuation(c);
bool canOpen = !CharHelper.IsWhiteSpaceOrZero(c) &&
(!afterIsPunctuation ||
!Utility.IsWhiteSpaceOrZero(pc) ||
!Utility.IsASCIIPunctuation(pc));
!CharHelper.IsWhiteSpaceOrZero(pc) ||
!CharHelper.IsAsciiPunctuation(pc));
// A right-flanking delimiter run is a delimiter run that is
@@ -53,11 +54,11 @@ namespace Textamina.Markdig.Syntax
// (b) either not preceded by a punctuation character, or followed by Unicode whitespace
// or a punctuation character.
// For purposes of this definition, the beginning and the end of the line count as Unicode whitespace.
var beforeIsPunctuation = Utility.IsASCIIPunctuation(pc);
bool canClose = !Utility.IsWhiteSpaceOrZero(pc) &&
var beforeIsPunctuation = CharHelper.IsAsciiPunctuation(pc);
bool canClose = !CharHelper.IsWhiteSpaceOrZero(pc) &&
(!beforeIsPunctuation ||
!Utility.IsWhiteSpaceOrZero(c) ||
!Utility.IsASCIIPunctuation(c));
!CharHelper.IsWhiteSpaceOrZero(c) ||
!CharHelper.IsAsciiPunctuation(c));
if (delimiterChar == '_')
{

3
src/Textamina.Markdig/Syntax/Inlines/EscapeInline.cs
View File

@@ -1,3 +1,4 @@
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -21,7 +22,7 @@ namespace Textamina.Markdig.Syntax
// Go to escape character
lines.NextChar();
if (Utility.IsASCIIPunctuation(lines.Current))
if (CharHelper.IsAsciiPunctuation(lines.Current))
{
state.Inline = new EscapeInline() {EscapedChar = lines.Current};
lines.NextChar();

11
src/Textamina.Markdig/Syntax/Inlines/LinkInline.cs
View File

@@ -1,6 +1,7 @@
using System;
using System.Text;
using Textamina.Markdig.Formatters;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -113,7 +114,7 @@ namespace Textamina.Markdig.Syntax
break;
}
if (hasEscape && !Utility.IsASCIIPunctuation(c))
if (hasEscape && !CharHelper.IsAsciiPunctuation(c))
{
buffer.Append('\\');
}
@@ -173,7 +174,7 @@ namespace Textamina.Markdig.Syntax
break;
}
if (hasEscape && !Utility.IsASCIIPunctuation(c))
if (hasEscape && !CharHelper.IsAsciiPunctuation(c))
{
buffer.Append('\\');
}
@@ -186,7 +187,7 @@ namespace Textamina.Markdig.Syntax
hasEscape = false;
if (Utility.IsWhitespace(c)) // TODO: specs unclear. space is strict or relaxed? (includes tabs?)
if (CharHelper.IsWhitespace(c)) // TODO: specs unclear. space is strict or relaxed? (includes tabs?)
{
break;
}
@@ -231,7 +232,7 @@ namespace Textamina.Markdig.Syntax
}
}
if (hasEscape && !Utility.IsASCIIPunctuation(c))
if (hasEscape && !CharHelper.IsAsciiPunctuation(c))
{
buffer.Append('\\');
}
@@ -246,7 +247,7 @@ namespace Textamina.Markdig.Syntax
hasEscape = false;
if (Utility.IsSpaceOrTab(c) || Utility.IsControl(c)) // TODO: specs unclear. space is strict or relaxed? (includes tabs?)
if (CharHelper.IsSpaceOrTab(c) || CharHelper.IsControl(c)) // TODO: specs unclear. space is strict or relaxed? (includes tabs?)
{
isValid = true;
break;

8
src/Textamina.Markdig/Syntax/ListBlock.cs
View File

@@ -1,5 +1,7 @@
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -48,7 +50,7 @@ namespace Textamina.Markdig.Syntax
var c = liner.Current;
var startPosition = liner.Column;
while (Utility.IsSpaceOrTab(c))
while (CharHelper.IsSpaceOrTab(c))
{
c = liner.NextChar();
var endPosition = liner.Column;
@@ -71,7 +73,7 @@ namespace Textamina.Markdig.Syntax
liner.SkipLeadingSpaces3();
var preIndent = liner.Start - preStartPosition;
var c = liner.Current;
if (Utility.IsBulletListMarker(c))
if (CharHelper.IsBulletListMarker(c))
{
var listType = c;
@@ -82,7 +84,7 @@ namespace Textamina.Markdig.Syntax
for (int i = 0; i < 4; i++)
{
c = liner.NextChar();
if (!Utility.IsSpaceOrTab(c))
if (!CharHelper.IsSpaceOrTab(c))
{
break;
}

7
src/Textamina.Markdig/Syntax/ParagraphBlock.cs
View File

@@ -1,6 +1,7 @@
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -55,7 +56,7 @@ namespace Textamina.Markdig.Syntax
if (checkForSpaces)
{
if (!Utility.IsSpaceOrTab(c))
if (!CharHelper.IsSpaceOrTab(c))
{
headingChar = (char)0;
break;
@@ -63,7 +64,7 @@ namespace Textamina.Markdig.Syntax
}
else if (c != headingChar)
{
if (Utility.IsSpaceOrTab(c))
if (CharHelper.IsSpaceOrTab(c))
{
checkForSpaces = true;
}
@@ -93,7 +94,7 @@ namespace Textamina.Markdig.Syntax
{
// Remove leading spaces from paragraph
var c = liner.Current;
while (Utility.IsSpaceOrTab(c))
while (CharHelper.IsSpaceOrTab(c))
{
c = liner.NextChar();
}

5
src/Textamina.Markdig/Syntax/QuoteBlock.cs
View File

@@ -1,4 +1,5 @@
using Textamina.Markdig.Parsing;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
{
@@ -23,7 +24,7 @@ namespace Textamina.Markdig.Syntax
}
c = liner.NextChar();
if (Utility.IsSpace(c))
if (CharHelper.IsSpace(c))
{
liner.NextChar();
}

11
src/Textamina.Markdig/Syntax/StringLine.cs
View File

@@ -1,5 +1,6 @@
using System;
using System.Runtime.CompilerServices;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -63,7 +64,7 @@ namespace Textamina.Markdig.Syntax
{
// If previous character was a tab make the Column += 4
Column++;
if (Utility.IsTab(Current))
if (CharHelper.IsTab(Current))
{
// Align the tab on a column
Column = ((Column + 3) / 4) * 4;
@@ -156,7 +157,7 @@ namespace Textamina.Markdig.Syntax
for (int i = Start; i <= End; i++)
{
if (!Utility.IsSpace(Text[i]))
if (!CharHelper.IsSpace(Text[i]))
{
return false;
}
@@ -169,7 +170,7 @@ namespace Textamina.Markdig.Syntax
{
for (int i = 0; i < 3; i++)
{
if (!Utility.IsSpace(Current))
if (!CharHelper.IsSpace(Current))
{
break;
}
@@ -186,7 +187,7 @@ namespace Textamina.Markdig.Syntax
{
// Strip leading spaces
var c = Current;
while (Utility.IsSpace(c))
while (CharHelper.IsSpace(c))
{
c = NextChar();
}
@@ -197,7 +198,7 @@ namespace Textamina.Markdig.Syntax
for (int i = End; i >= Start; i--)
{
End = i;
if (!Utility.IsSpace(this[i]))
if (!CharHelper.IsSpace(this[i]))
{
break;
}

3
src/Textamina.Markdig/Syntax/StringLineGroup.cs
View File

@@ -1,6 +1,7 @@
using System;
using System.Collections.ObjectModel;
using System.Text;
using Textamina.Markdig.Helpers;
using Textamina.Markdig.Parsing;
namespace Textamina.Markdig.Syntax
@@ -124,7 +125,7 @@ namespace Textamina.Markdig.Syntax
public bool SkipWhiteSpaces()
{
bool hasWhitespaces = false;
while (Utility.IsWhitespace(Current))
while (CharHelper.IsWhitespace(Current))
{
NextChar();
hasWhitespaces = true;

7
src/Textamina.Markdig/Textamina.Markdig.csproj
View File

@@ -35,11 +35,10 @@
<WarningLevel>4</WarningLevel>
</PropertyGroup>
<ItemGroup>
<Compile Include="Formatters\EntityDecoder.cs" />
<Compile Include="Helpers\EntityHelper.cs" />
<Compile Include="Formatters\HtmlFormatter.cs" />
<Compile Include="Formatters\HtmlHelper.cs" />
<Compile Include="Helpers\HtmlHelper.cs" />
<Compile Include="Formatters\HtmlTextWriter.cs" />
<Compile Include="Formatters\Scanner.cs" />
<Compile Include="Parsing\InlineParser.cs" />
<Compile Include="Parsing\MatchInlineState.cs" />
<Compile Include="Parsing\MatchLineState.cs" />
@@ -74,7 +73,7 @@
<Compile Include="Syntax\ListItemBlock.cs" />
<Compile Include="Syntax\QuoteBlock.cs" />
<Compile Include="Syntax\BreakBlock.cs" />
<Compile Include="Utility.cs" />
<Compile Include="Helpers\CharHelper.cs" />
<Compile Include="Syntax\CodeBlock.cs" />
<Compile Include="Syntax\Document.cs" />
<Compile Include="Syntax\FencedCodeBlock.cs" />