Mirrors/SubtitleEdit
1
0
Fork 0
mirror of https://github.com/SubtitleEdit/subtitleedit.git synced 2025-02-01 05:21:40 +01:00
Code Issues Projects Releases Wiki Activity

Merge pull request #2091 from ivandrofly/strippable

Browse Source 
[Rename] - Stripable => Strippable.
This commit is contained in:
Nikolaj Olsson 2016-11-20 07:56:53 +01:00 committed by GitHub
commit 96b01df184
16 changed files with 341 additions and 341 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
libse/Forms/FixCommonErrors/FixMissingPeriodsAtEndOfLine.cs
View File

@ -101,7 +101,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
{
if (p.Text != p.Text.ToUpper())
{
var st = new StripableText(next.Text);
var st = new StrippableText(next.Text);
if (st.StrippedText.Length > 0 && st.StrippedText != st.StrippedText.ToUpper() &&
char.IsUpper(st.StrippedText[0]))
{
@ -139,7 +139,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
string oldText = p.Text;
string text = p.Text.Substring(0, indexOfNewLine);
var st = new StripableText(text);
var st = new StrippableText(text);
if (st.Pre.TrimEnd().EndsWith('¿')) // Spanish ¿
p.Text = p.Text.Insert(indexOfNewLine, "?");
else if (st.Pre.TrimEnd().EndsWith('¡')) // Spanish ¡

2
libse/Forms/FixCommonErrors/FixSpanishInvertedQuestionAndExclamationMarks.cs
View File

@ -121,7 +121,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
part = part.Substring(speakerEnd + 1);
}
var st = new StripableText(part);
var st = new StrippableText(part);
if (j == 0 && mark == '!' && st.Pre == "¿" && Utilities.CountTagInText(p.Text, mark) == 1 && HtmlUtil.RemoveHtmlTags(p.Text).EndsWith(mark))
{
p.Text = inverseMark + p.Text;

2
libse/Forms/FixCommonErrors/FixStartWithUppercaseLetterAfterColon.cs
View File

@ -23,7 +23,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
string lastText = HtmlUtil.RemoveHtmlTags(last.Text);
if (lastText.EndsWith(':') || lastText.EndsWith(';'))
{
var st = new StripableText(p.Text);
var st = new StrippableText(p.Text);
if (st.StrippedText.Length > 0 && st.StrippedText[0] != char.ToUpper(st.StrippedText[0]))
p.Text = st.Pre + char.ToUpper(st.StrippedText[0]) + st.StrippedText.Substring(1) + st.Post;
}

2
libse/Forms/FixCommonErrors/FixStartWithUppercaseLetterAfterParagraph.cs
View File

@ -259,7 +259,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
if (indexOfNewLine > 0)
{
string text = p.Text.Substring(indexOfNewLine + len);
var st = new StripableText(text);
var st = new StrippableText(text);
if (st.StrippedText.Length > 0 && Helper.IsTurkishLittleI(st.StrippedText[0], encoding, language) && !st.Pre.EndsWith('[') && !st.Pre.Contains("..."))
{

4
libse/Forms/FixCommonErrors/FixStartWithUppercaseLetterAfterPeriodInsideParagraph.cs
View File

@ -35,7 +35,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
string oldText = p.Text;
if (p.Text.Length > 3 && callbacks.AllowFix(p, fixAction))
{
var st = new StripableText(p.Text);
var st = new StrippableText(p.Text);
string text = st.StrippedText;
int start = text.IndexOfAny(ExpectedChars);
while (start > 0 && start < text.Length)
@ -51,7 +51,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
}
if ((start + 3 < text.Length) && (text[start + 1] == ' ') && !IsAbbreviation(text, start, callbacks))
{
var subText = new StripableText(text.Substring(start + 2));
var subText = new StrippableText(text.Substring(start + 2));
text = text.Substring(0, start + 2) + subText.CombineWithPrePost(ToUpperFirstLetter(subText.StrippedText, callbacks));
}
// Try to reach the last dot if char at *start is '.'.

2
libse/Forms/FixCommonErrors/FixUppercaseIInsideWords.cs
View File

@ -35,7 +35,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
match = match.NextMatch();
}
var st = new StripableText(p.Text);
var st = new StrippableText(p.Text);
match = ReBeforeLowercaseLetter.Match(st.StrippedText);
while (match.Success)
{

8
libse/Forms/FixCommonErrors/Helper.cs
View File

@ -269,16 +269,16 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
if (remove)
{
int idx = text.IndexOf('-');
var st = new StripableText(text);
var st = new StrippableText(text);
if (idx < 5 && st.Pre.Length >= idx)
{
text = text.Remove(idx, 1).TrimStart();
idx = text.IndexOf('-');
st = new StripableText(text);
st = new StrippableText(text);
if (idx < 5 && idx >= 0 && st.Pre.Length >= idx)
{
text = text.Remove(idx, 1).TrimStart();
st = new StripableText(text);
st = new StrippableText(text);
}
idx = text.IndexOf('-');
if (idx < 5 && idx >= 0 && st.Pre.Length >= idx)
@ -315,7 +315,7 @@ namespace Nikse.SubtitleEdit.Core.Forms.FixCommonErrors
var prev = subtitle.GetParagraphOrDefault(i - 1);
if (prev == null || !HtmlUtil.RemoveHtmlTags(prev.Text).TrimEnd().EndsWith('-') || HtmlUtil.RemoveHtmlTags(prev.Text).TrimEnd().EndsWith("--", StringComparison.Ordinal))
{
var st = new StripableText(text);
var st = new StrippableText(text);
if (st.Pre.EndsWith('-') || st.Pre.EndsWith("- ", StringComparison.Ordinal))
{
text = st.Pre.TrimEnd('-', ' ') + st.StrippedText + st.Post;

30
libse/Forms/RemoveTextForHI.cs
View File

@ -184,7 +184,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
}
else
{
var preStripable = new StripableText(pre);
var preStrippable = new StrippableText(pre);
var remove = true;
if (indexOfColon < line.Length - 1)
@ -243,7 +243,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
else if (newText.EndsWith("</u>", StringComparison.Ordinal) && text.StartsWith("<u>", StringComparison.Ordinal) && !newText.StartsWith("<u>", StringComparison.Ordinal))
newText = "<u>" + newText;
if (!IsHIDescription(preStripable.StrippedText))
if (!IsHIDescription(preStrippable.StrippedText))
noOfNames++;
}
else
@ -324,9 +324,9 @@ namespace Nikse.SubtitleEdit.Core.Forms
var arr = newText.SplitToLines();
if (arr.Length == 2 && arr[0].Length > 1 && arr[1].Length > 1)
{
string arr0 = new StripableText(arr[0]).StrippedText;
var arr1Stripable = new StripableText(arr[1]);
string arr1 = arr1Stripable.StrippedText;
string arr0 = new StrippableText(arr[0]).StrippedText;
var arr1Strippable = new StrippableText(arr[1]);
string arr1 = arr1Strippable.StrippedText;
if (arr0.Length > 0 && arr1.Length > 1)
{
@ -336,7 +336,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
char c = arr0[arr0.Length - 1];
if (char.IsLower(c) || c == ',') // first line ends with comma or lower case letter
{
if (!arr1Stripable.Pre.Contains("..."))
if (!arr1Strippable.Pre.Contains("..."))
{
insertDash = false;
}
@ -348,7 +348,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
string arr0QuoteTrimmed = arr[0].TrimEnd('"');
if (arr0QuoteTrimmed.Length > 0 && !".?!".Contains(arr0QuoteTrimmed[arr0QuoteTrimmed.Length - 1]) && !arr0QuoteTrimmed.EndsWith("</i>", StringComparison.Ordinal) && !arr0QuoteTrimmed.EndsWith("--", StringComparison.Ordinal) && !arr0QuoteTrimmed.EndsWith("—", StringComparison.Ordinal))
{
if (!arr1Stripable.Pre.Contains('-'))
if (!arr1Strippable.Pre.Contains('-'))
{
insertDash = false;
}
@ -367,7 +367,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
{
if (indexOfDialogChar < 0 || indexOfDialogChar > 4)
{
var st = new StripableText(newText, string.Empty, string.Empty);
var st = new StrippableText(newText, string.Empty, string.Empty);
newText = st.Pre + "- " + st.StrippedText + st.Post;
}
@ -380,7 +380,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
}
if ((indexOfDialogChar < 0 || indexOfDialogChar > 6) && !second.StartsWith('-'))
{
var st = new StripableText(second, String.Empty, String.Empty);
var st = new StrippableText(second, String.Empty, String.Empty);
second = st.Pre + "- " + st.StrippedText + st.Post;
newText = newText.Remove(indexOfNewLine) + Environment.NewLine + second;
}
@ -388,7 +388,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
}
else if (newText.Contains('-') && !newText.Contains(Environment.NewLine))
{
var st = new StripableText(newText);
var st = new StrippableText(newText);
if (st.Pre.Contains('-'))
newText = st.Pre.Replace("-", string.Empty) + st.StrippedText + st.Post;
}
@ -467,7 +467,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
pre = pre.Replace(Settings.CustomStart, string.Empty);
post = post.Replace(Settings.CustomEnd, string.Empty);
}
var st = new StripableText(text, pre, post);
var st = new StrippableText(text, pre, post);
var sb = new StringBuilder();
var parts = st.StrippedText.Trim().SplitToLines();
int lineNumber = 0;
@ -476,7 +476,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
int noOfNamesRemovedNotInLineOne = 0;
foreach (string s in parts)
{
var stSub = new StripableText(s, pre, post);
var stSub = new StrippableText(s, pre, post);
string strippedText = stSub.StrippedText;
if ((lineNumber == parts.Length - 1 && st.Post.Contains('?')) || stSub.Post.Contains('?'))
strippedText += "?";
@ -561,7 +561,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
if (Settings.RemoveInterjections)
text = RemoveInterjections(text);
st = new StripableText(text, " >-\"'‘`´♪¿¡.…—", " -\"'`´♪.!?:…—");
st = new StrippableText(text, " >-\"'‘`´♪¿¡.…—", " -\"'`´♪.!?:…—");
text = st.StrippedText;
if (StartsAndEndsWithHearImpairedTags(text))
{
@ -577,7 +577,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
var splitParts = HtmlUtil.RemoveHtmlTags(text).Replace(" ", string.Empty).Split(splitChars, StringSplitOptions.RemoveEmptyEntries);
if (splitParts.Length == 2)
{
var temp = new StripableText(text);
var temp = new StrippableText(text);
temp.StrippedText = temp.StrippedText.Replace(Environment.NewLine, " ");
int splitIndex = temp.StrippedText.LastIndexOfAny(splitChars);
if (splitIndex > 0)
@ -1017,7 +1017,7 @@ namespace Nikse.SubtitleEdit.Core.Forms
if (temp.EndsWith(Environment.NewLine + "- ", StringComparison.Ordinal))
temp = temp.Remove(temp.Length - 2).TrimEnd();
var st = new StripableText(temp);
var st = new StrippableText(temp);
if (st.StrippedText.Length == 0)
return string.Empty;

2
libse/LibSE.csproj
View File

@ -190,7 +190,7 @@
<Compile Include="SpellCheck\UndoObject.cs" />
<Compile Include="SsaStyle.cs" />
<Compile Include="StringExtensions.cs" />
<Compile Include="StripableText.cs" />
<Compile Include="StrippableText.cs" />
<Compile Include="SubtitleEditRegex.cs" />
<Compile Include="Subtitle.cs" />
<Compile Include="SubtitleFormats\AribB36.cs" />

562
libse/StripableText.cs → libse/StrippableText.cs
View File

@ -1,281 +1,281 @@
using System;
using System.Collections.Generic;
using System.Text;
namespace Nikse.SubtitleEdit.Core
{
public class StripableText
{
public string Pre { get; set; }
public string Post { get; set; }
public string StrippedText { get; set; }
public string OriginalText { get; private set; }
public string MergedString
{
get { return Pre + StrippedText + Post; }
}
public StripableText(string text)
: this(text, " >-\"”“['‘`´¶(♪¿¡.…—", " -\"”“]'`´¶)♪.!?:…—")
{
}
public StripableText(string text, string stripStartCharacters, string stripEndCharacters)
{
OriginalText = text;
Pre = string.Empty;
if (text.Length > 0 && ("<{" + stripStartCharacters).Contains(text[0]))
{
int beginLength;
do
{
beginLength = text.Length;
while (text.Length > 0 && stripStartCharacters.Contains(text[0]))
{
Pre += text[0];
text = text.Remove(0, 1);
}
// ASS/SSA codes like {\an9}
int endIndex = text.IndexOf('}');
if (endIndex > 0 && text.StartsWith("{\\", StringComparison.Ordinal))
{
int nextStartIndex = text.IndexOf('{', 2);
if (nextStartIndex == -1 || nextStartIndex > endIndex)
{
endIndex++;
Pre += text.Substring(0, endIndex);
text = text.Remove(0, endIndex);
}
}
// tags like <i> or <font face="Segoe Print" color="#ff0000">
endIndex = text.IndexOf('>');
if (text.StartsWith('<') && endIndex >= 2)
{
endIndex++;
Pre += text.Substring(0, endIndex);
text = text.Remove(0, endIndex);
}
}
while (text.Length < beginLength);
}
Post = string.Empty;
if (text.Length > 0 && (">" + stripEndCharacters).Contains(text[text.Length - 1]))
{
int beginLength;
do
{
beginLength = text.Length;
while (text.Length > 0 && stripEndCharacters.Contains(text[text.Length - 1]))
{
Post = text[text.Length - 1] + Post;
text = text.Substring(0, text.Length - 1);
}
if (text.EndsWith('>'))
{
// tags </i> </b> </u>
if (text.EndsWith("</i>", StringComparison.OrdinalIgnoreCase) ||
text.EndsWith("</b>", StringComparison.OrdinalIgnoreCase) ||
text.EndsWith("</u>", StringComparison.OrdinalIgnoreCase))
{
Post = text.Substring(text.Length - 4) + Post;
text = text.Substring(0, text.Length - 4);
}
// tag </font>
if (text.EndsWith("</font>", StringComparison.OrdinalIgnoreCase))
{
Post = text.Substring(text.Length - 7) + Post;
text = text.Substring(0, text.Length - 7);
}
}
}
while (text.Length < beginLength);
}
StrippedText = text;
}
private static string GetAndInsertNextId(List<string> replaceIds, List<string> replaceNames, string name, int idName)
{
string id = $"_@{idName}_";
replaceIds.Add(id);
replaceNames.Add(name);
return id;
}
private void ReplaceNames1Remove(List<string> namesEtc, List<string> replaceIds, List<string> replaceNames, List<string> originalNames)
{
if (Post.StartsWith('.'))
{
StrippedText += ".";
Post = Post.Remove(0, 1);
}
string lower = StrippedText.ToLower();
int idName = 0;
foreach (string name in namesEtc)
{
int start = lower.IndexOf(name, StringComparison.OrdinalIgnoreCase);
while (start >= 0 && start < lower.Length)
{
bool startOk = (start == 0) || (lower[start - 1] == ' ') || (lower[start - 1] == '-') ||
(lower[start - 1] == '"') || (lower[start - 1] == '\'') || (lower[start - 1] == '>') ||
Environment.NewLine.EndsWith(lower[start - 1]);
if (startOk && string.CompareOrdinal(name, "Don") == 0 && lower.Substring(start).StartsWith("don't"))
startOk = false;
if (startOk)
{
int end = start + name.Length;
bool endOk = end <= lower.Length;
if (endOk)
endOk = end == lower.Length || (@" ,.!?:;')- <""" + Environment.NewLine).Contains(lower[end]);
if (endOk && StrippedText.Length >= start + name.Length)
{
string originalName = StrippedText.Substring(start, name.Length);
originalNames.Add(originalName);
StrippedText = StrippedText.Remove(start, name.Length);
StrippedText = StrippedText.Insert(start, GetAndInsertNextId(replaceIds, replaceNames, name, idName++));
lower = StrippedText.ToLower();
}
}
if (start + 3 > lower.Length)
start = lower.Length + 1;
else
start = lower.IndexOf(name, start + 3, StringComparison.OrdinalIgnoreCase);
}
}
if (StrippedText.EndsWith('.'))
{
Post = "." + Post;
StrippedText = StrippedText.TrimEnd('.');
}
}
private void ReplaceNames2Fix(List<string> replaceIds, List<string> replaceNames)
{
for (int i = 0; i < replaceIds.Count; i++)
{
StrippedText = StrippedText.Replace(replaceIds[i], replaceNames[i]);
}
}
private static readonly char[] ExpectedCharsArray = { '.', '!', '?', ':', ';', ')', ']', '}', '(', '[', '{' };
public void FixCasing(List<string> namesEtc, bool changeNameCases, bool makeUppercaseAfterBreak, bool checkLastLine, string lastLine)
{
var replaceIds = new List<string>();
var replaceNames = new List<string>();
var originalNames = new List<string>();
ReplaceNames1Remove(namesEtc, replaceIds, replaceNames, originalNames);
if (checkLastLine)
{
string s = HtmlUtil.RemoveHtmlTags(lastLine).TrimEnd().TrimEnd('\"').TrimEnd();
bool startWithUppercase = string.IsNullOrEmpty(s) ||
s.EndsWith('.') ||
s.EndsWith('!') ||
s.EndsWith('?') ||
s.EndsWith(". ♪", StringComparison.Ordinal) ||
s.EndsWith("! ♪", StringComparison.Ordinal) ||
s.EndsWith("? ♪", StringComparison.Ordinal) ||
s.EndsWith(']') ||
s.EndsWith(')') ||
s.EndsWith(':');
// start with uppercase after music symbol - but only if next line does not start with music symbol
if (!startWithUppercase && (s.EndsWith('♪') || s.EndsWith('♫')))
{
if (!Pre.Contains(new[] { '♪', '♫' }))
startWithUppercase = true;
}
if (startWithUppercase && StrippedText.Length > 0 && !Pre.Contains("..."))
{
StrippedText = char.ToUpper(StrippedText[0]) + StrippedText.Substring(1);
}
}
if (makeUppercaseAfterBreak && StrippedText.Contains(ExpectedCharsArray))
{
const string breakAfterChars = @".!?:;)]}([{";
const string expectedChars = "\"`´'()<>!?.- \r\n";
var sb = new StringBuilder();
bool lastWasBreak = false;
for (int i = 0; i < StrippedText.Length; i++)
{
var s = StrippedText[i];
if (lastWasBreak)
{
if (expectedChars.Contains(s))
{
sb.Append(s);
}
else if ((sb.EndsWith('<') || sb.ToString().EndsWith("</", StringComparison.Ordinal)) && i + 1 < StrippedText.Length && StrippedText[i + 1] == '>')
{ // tags
sb.Append(s);
}
else if (sb.EndsWith('<') && s == '/' && i + 2 < StrippedText.Length && StrippedText[i + 2] == '>')
{ // tags
sb.Append(s);
}
else if (sb.ToString().EndsWith("... ", StringComparison.Ordinal))
{
sb.Append(s);
lastWasBreak = false;
}
else
{
if (breakAfterChars.Contains(s))
{
sb.Append(s);
}
else
{
lastWasBreak = false;
sb.Append(char.ToUpper(s));
}
}
}
else
{
sb.Append(s);
if (breakAfterChars.Contains(s))
{
var idx = sb.ToString().IndexOf('[');
if (s == ']' && idx > 1)
{ // I [Motor roaring] love you!
string temp = sb.ToString(0, idx - 1).Trim();
if (temp.Length > 0 && !char.IsLower(temp[temp.Length - 1]))
lastWasBreak = true;
}
else
{
lastWasBreak = true;
}
}
}
}
StrippedText = sb.ToString();
}
ReplaceNames2Fix(replaceIds, changeNameCases ? replaceNames : originalNames);
}
public string CombineWithPrePost(string text)
{
return Pre + text + Post;
}
}
}
using System;
using System.Collections.Generic;
using System.Text;
namespace Nikse.SubtitleEdit.Core
{
public class StrippableText
{
public string Pre { get; set; }
public string Post { get; set; }
public string StrippedText { get; set; }
public string OriginalText { get; private set; }
public string MergedString
{
get { return Pre + StrippedText + Post; }
}
public StrippableText(string text)
: this(text, " >-\"”“['‘`´¶(♪¿¡.…—", " -\"”“]'`´¶)♪.!?:…—")
{
}
public StrippableText(string text, string stripStartCharacters, string stripEndCharacters)
{
OriginalText = text;
Pre = string.Empty;
if (text.Length > 0 && ("<{" + stripStartCharacters).Contains(text[0]))
{
int beginLength;
do
{
beginLength = text.Length;
while (text.Length > 0 && stripStartCharacters.Contains(text[0]))
{
Pre += text[0];
text = text.Remove(0, 1);
}
// ASS/SSA codes like {\an9}
int endIndex = text.IndexOf('}');
if (endIndex > 0 && text.StartsWith("{\\", StringComparison.Ordinal))
{
int nextStartIndex = text.IndexOf('{', 2);
if (nextStartIndex == -1 || nextStartIndex > endIndex)
{
endIndex++;
Pre += text.Substring(0, endIndex);
text = text.Remove(0, endIndex);
}
}
// tags like <i> or <font face="Segoe Print" color="#ff0000">
endIndex = text.IndexOf('>');
if (text.StartsWith('<') && endIndex >= 2)
{
endIndex++;
Pre += text.Substring(0, endIndex);
text = text.Remove(0, endIndex);
}
}
while (text.Length < beginLength);
}
Post = string.Empty;
if (text.Length > 0 && (">" + stripEndCharacters).Contains(text[text.Length - 1]))
{
int beginLength;
do
{
beginLength = text.Length;
while (text.Length > 0 && stripEndCharacters.Contains(text[text.Length - 1]))
{
Post = text[text.Length - 1] + Post;
text = text.Substring(0, text.Length - 1);
}
if (text.EndsWith('>'))
{
// tags </i> </b> </u>
if (text.EndsWith("</i>", StringComparison.OrdinalIgnoreCase) ||
text.EndsWith("</b>", StringComparison.OrdinalIgnoreCase) ||
text.EndsWith("</u>", StringComparison.OrdinalIgnoreCase))
{
Post = text.Substring(text.Length - 4) + Post;
text = text.Substring(0, text.Length - 4);
}
// tag </font>
if (text.EndsWith("</font>", StringComparison.OrdinalIgnoreCase))
{
Post = text.Substring(text.Length - 7) + Post;
text = text.Substring(0, text.Length - 7);
}
}
}
while (text.Length < beginLength);
}
StrippedText = text;
}
private static string GetAndInsertNextId(List<string> replaceIds, List<string> replaceNames, string name, int idName)
{
string id = $"_@{idName}_";
replaceIds.Add(id);
replaceNames.Add(name);
return id;
}
private void ReplaceNames1Remove(List<string> namesEtc, List<string> replaceIds, List<string> replaceNames, List<string> originalNames)
{
if (Post.StartsWith('.'))
{
StrippedText += ".";
Post = Post.Remove(0, 1);
}
string lower = StrippedText.ToLower();
int idName = 0;
foreach (string name in namesEtc)
{
int start = lower.IndexOf(name, StringComparison.OrdinalIgnoreCase);
while (start >= 0 && start < lower.Length)
{
bool startOk = (start == 0) || (lower[start - 1] == ' ') || (lower[start - 1] == '-') ||
(lower[start - 1] == '"') || (lower[start - 1] == '\'') || (lower[start - 1] == '>') ||
Environment.NewLine.EndsWith(lower[start - 1]);
if (startOk && string.CompareOrdinal(name, "Don") == 0 && lower.Substring(start).StartsWith("don't"))
startOk = false;
if (startOk)
{
int end = start + name.Length;
bool endOk = end <= lower.Length;
if (endOk)
endOk = end == lower.Length || (@" ,.!?:;')- <""" + Environment.NewLine).Contains(lower[end]);
if (endOk && StrippedText.Length >= start + name.Length)
{
string originalName = StrippedText.Substring(start, name.Length);
originalNames.Add(originalName);
StrippedText = StrippedText.Remove(start, name.Length);
StrippedText = StrippedText.Insert(start, GetAndInsertNextId(replaceIds, replaceNames, name, idName++));
lower = StrippedText.ToLower();
}
}
if (start + 3 > lower.Length)
start = lower.Length + 1;
else
start = lower.IndexOf(name, start + 3, StringComparison.OrdinalIgnoreCase);
}
}
if (StrippedText.EndsWith('.'))
{
Post = "." + Post;
StrippedText = StrippedText.TrimEnd('.');
}
}
private void ReplaceNames2Fix(List<string> replaceIds, List<string> replaceNames)
{
for (int i = 0; i < replaceIds.Count; i++)
{
StrippedText = StrippedText.Replace(replaceIds[i], replaceNames[i]);
}
}
private static readonly char[] ExpectedCharsArray = { '.', '!', '?', ':', ';', ')', ']', '}', '(', '[', '{' };
public void FixCasing(List<string> namesEtc, bool changeNameCases, bool makeUppercaseAfterBreak, bool checkLastLine, string lastLine)
{
var replaceIds = new List<string>();
var replaceNames = new List<string>();
var originalNames = new List<string>();
ReplaceNames1Remove(namesEtc, replaceIds, replaceNames, originalNames);
if (checkLastLine)
{
string s = HtmlUtil.RemoveHtmlTags(lastLine).TrimEnd().TrimEnd('\"').TrimEnd();
bool startWithUppercase = string.IsNullOrEmpty(s) ||
s.EndsWith('.') ||
s.EndsWith('!') ||
s.EndsWith('?') ||
s.EndsWith(". ♪", StringComparison.Ordinal) ||
s.EndsWith("! ♪", StringComparison.Ordinal) ||
s.EndsWith("? ♪", StringComparison.Ordinal) ||
s.EndsWith(']') ||
s.EndsWith(')') ||
s.EndsWith(':');
// start with uppercase after music symbol - but only if next line does not start with music symbol
if (!startWithUppercase && (s.EndsWith('♪') || s.EndsWith('♫')))
{
if (!Pre.Contains(new[] { '♪', '♫' }))
startWithUppercase = true;
}
if (startWithUppercase && StrippedText.Length > 0 && !Pre.Contains("..."))
{
StrippedText = char.ToUpper(StrippedText[0]) + StrippedText.Substring(1);
}
}
if (makeUppercaseAfterBreak && StrippedText.Contains(ExpectedCharsArray))
{
const string breakAfterChars = @".!?:;)]}([{";
const string expectedChars = "\"`´'()<>!?.- \r\n";
var sb = new StringBuilder();
bool lastWasBreak = false;
for (int i = 0; i < StrippedText.Length; i++)
{
var s = StrippedText[i];
if (lastWasBreak)
{
if (expectedChars.Contains(s))
{
sb.Append(s);
}
else if ((sb.EndsWith('<') || sb.ToString().EndsWith("</", StringComparison.Ordinal)) && i + 1 < StrippedText.Length && StrippedText[i + 1] == '>')
{ // tags
sb.Append(s);
}
else if (sb.EndsWith('<') && s == '/' && i + 2 < StrippedText.Length && StrippedText[i + 2] == '>')
{ // tags
sb.Append(s);
}
else if (sb.ToString().EndsWith("... ", StringComparison.Ordinal))
{
sb.Append(s);
lastWasBreak = false;
}
else
{
if (breakAfterChars.Contains(s))
{
sb.Append(s);
}
else
{
lastWasBreak = false;
sb.Append(char.ToUpper(s));
}
}
}
else
{
sb.Append(s);
if (breakAfterChars.Contains(s))
{
var idx = sb.ToString().IndexOf('[');
if (s == ']' && idx > 1)
{ // I [Motor roaring] love you!
string temp = sb.ToString(0, idx - 1).Trim();
if (temp.Length > 0 && !char.IsLower(temp[temp.Length - 1]))
lastWasBreak = true;
}
else
{
lastWasBreak = true;
}
}
}
}
StrippedText = sb.ToString();
}
ReplaceNames2Fix(replaceIds, changeNameCases ? replaceNames : originalNames);
}
public string CombineWithPrePost(string text)
{
return Pre + text + Post;
}
}
}

4
src/Forms/ChangeCasing.cs
View File

@ -110,14 +110,14 @@ namespace Nikse.SubtitleEdit.Forms
// first all to lower
text = text.ToLower().Trim();
text = text.FixExtraSpaces();
var st = new StripableText(text);
var st = new StrippableText(text);
st.FixCasing(namesEtc, false, true, true, lastLine); // fix all casing but names (that's a seperate option)
text = st.MergedString;
}
}
else if (radioButtonUppercase.Checked)
{
var st = new StripableText(text);
var st = new StrippableText(text);
text = st.Pre + st.StrippedText.ToUpper() + st.Post;
text = HtmlUtil.FixUpperTags(text); // tags inside text
}

2
src/Forms/ChangeCasingNames.cs
View File

@ -85,7 +85,7 @@ namespace Nikse.SubtitleEdit.Forms
{
if (item.Checked && text != null && text.Contains(name, StringComparison.OrdinalIgnoreCase) && name.Length > 1 && name != name.ToLower())
{
var st = new StripableText(text);
var st = new StrippableText(text);
st.FixCasing(new List<string> { name }, true, false, false, string.Empty);
text = st.MergedString;
}

2
src/Forms/ImportText.cs
View File

@ -220,7 +220,7 @@ namespace Nikse.SubtitleEdit.Forms
if (merge && (p.Text.TrimEnd().EndsWith('!') || p.Text.TrimEnd().EndsWith('.')))
{
var st = new StripableText(p.Text);
var st = new StrippableText(p.Text);
if (st.StrippedText.Length > 0 && char.IsUpper(st.StrippedText[0]))
merge = false;
}

4
src/Logic/OCR/OcrFixEngine.cs
View File

@ -642,7 +642,7 @@ namespace Nikse.SubtitleEdit.Logic.Ocr
lastLine.EndsWith('!') ||
lastLine.EndsWith('?'))
{
var st = new StripableText(l);
var st = new StrippableText(l);
if (st.StrippedText.StartsWith('i') && !st.Pre.EndsWith('[') && !st.Pre.EndsWith('(') && !st.Pre.EndsWith("...", StringComparison.Ordinal))
{
if (string.IsNullOrEmpty(lastLine) || (!lastLine.EndsWith("...", StringComparison.Ordinal) && !EndsWithAbbreviation(lastLine, _abbreviationList)))
@ -815,7 +815,7 @@ namespace Nikse.SubtitleEdit.Logic.Ocr
lastLine.EndsWith('♪'))
{
lastLine = HtmlUtil.RemoveHtmlTags(lastLine);
var st = new StripableText(input);
var st = new StrippableText(input);
if (lastLine == null || (!lastLine.EndsWith("...", StringComparison.Ordinal) && !EndsWithAbbreviation(lastLine, abbreviationList)))
{
if (st.StrippedText.Length > 0 && !char.IsUpper(st.StrippedText[0]) && !st.Pre.EndsWith('[') && !st.Pre.EndsWith('(') && !st.Pre.EndsWith("..."))

50
src/Test/Logic/StripableTextTest.cs → src/Test/Logic/StrippableTextTest.cs
View File

@ -4,112 +4,112 @@ using Nikse.SubtitleEdit.Core;
namespace Test.Logic
{
[TestClass]
public class StripableTextTest
public class StrippableTextTest
{
[TestMethod]
public void StripableTextItalic()
public void StrippableTextItalic()
{
var st = new StripableText("<i>Hi!</i>");
var st = new StrippableText("<i>Hi!</i>");
Assert.AreEqual(st.Pre, "<i>");
Assert.AreEqual(st.Post, "!</i>");
Assert.AreEqual(st.StrippedText, "Hi");
}
[TestMethod]
public void StripableTextAss()
public void StrippableTextAss()
{
var st = new StripableText("{\\an9}Hi!");
var st = new StrippableText("{\\an9}Hi!");
Assert.AreEqual(st.Pre, "{\\an9}");
Assert.AreEqual(st.Post, "!");
Assert.AreEqual(st.StrippedText, "Hi");
}
[TestMethod]
public void StripableTextFont()
public void StrippableTextFont()
{
var st = new StripableText("<font color=\"red\">Hi!</font>");
var st = new StrippableText("<font color=\"red\">Hi!</font>");
Assert.AreEqual(st.Pre, "<font color=\"red\">");
Assert.AreEqual(st.Post, "!</font>");
Assert.AreEqual(st.StrippedText, "Hi");
}
[TestMethod]
public void StripableTextItalic2()
public void StrippableTextItalic2()
{
var st = new StripableText("<i>O</i>");
var st = new StrippableText("<i>O</i>");
Assert.AreEqual(st.Pre, "<i>");
Assert.AreEqual(st.Post, "</i>");
Assert.AreEqual(st.StrippedText, "O");
}
[TestMethod]
public void StripableTextItalic3()
public void StrippableTextItalic3()
{
var st = new StripableText("<i>Hi!");
var st = new StrippableText("<i>Hi!");
Assert.AreEqual(st.Pre, "<i>");
Assert.AreEqual(st.Post, "!");
Assert.AreEqual(st.StrippedText, "Hi");
}
[TestMethod]
public void StripableTextFontDontTouch()
public void StrippableTextFontDontTouch()
{
var st = new StripableText("{MAN} Hi, how are you today!");
var st = new StrippableText("{MAN} Hi, how are you today!");
Assert.AreEqual(st.Pre, "");
Assert.AreEqual(st.Post, "!");
Assert.AreEqual(st.StrippedText, "{MAN} Hi, how are you today");
}
[TestMethod]
public void StripableOnlyPre()
public void StrippableOnlyPre()
{
var st = new StripableText("(");
var st = new StrippableText("(");
Assert.AreEqual(st.Pre, "(");
Assert.AreEqual(st.Post, "");
Assert.AreEqual(st.StrippedText, "");
}
[TestMethod]
public void StripableOnlyPre2()
public void StrippableOnlyPre2()
{
var st = new StripableText("<");
var st = new StrippableText("<");
Assert.AreEqual(st.Pre, "");
Assert.AreEqual(st.Post, "");
Assert.AreEqual(st.StrippedText, "<");
}
[TestMethod]
public void StripableOnlyPre3()
public void StrippableOnlyPre3()
{
var st = new StripableText("<i>");
var st = new StrippableText("<i>");
Assert.AreEqual(st.Pre, "<i>");
Assert.AreEqual(st.Post, "");
Assert.AreEqual(st.StrippedText, "");
}
[TestMethod]
public void StripableOnlyText()
public void StrippableOnlyText()
{
var st = new StripableText("H");
var st = new StrippableText("H");
Assert.AreEqual(st.Pre, "");
Assert.AreEqual(st.Post, "");
Assert.AreEqual(st.StrippedText, "H");
}
[TestMethod]
public void StripableTextItalicAndFont()
public void StrippableTextItalicAndFont()
{
var st = new StripableText("<i><font color=\"red\">Hi!</font></i>");
var st = new StrippableText("<i><font color=\"red\">Hi!</font></i>");
Assert.AreEqual(st.Pre, "<i><font color=\"red\">");
Assert.AreEqual(st.Post, "!</font></i>");
Assert.AreEqual(st.StrippedText, "Hi");
}
[TestMethod]
public void StripableTextItalicAndMore()
public void StrippableTextItalicAndMore()
{
var st = new StripableText("<i>...<b>Hi!</b></i>");
var st = new StrippableText("<i>...<b>Hi!</b></i>");
Assert.AreEqual(st.Pre, "<i>...<b>");
Assert.AreEqual(st.Post, "!</b></i>");
Assert.AreEqual(st.StrippedText, "Hi");

2
src/Test/Test.csproj
View File

@ -61,7 +61,7 @@
<Compile Include="Logic\TarFileTest.cs" />
<Compile Include="Logic\TransportStream\TransportStreamTest.cs" />
<Compile Include="Logic\ParagraphTest.cs" />
<Compile Include="Logic\StripableTextTest.cs" />
<Compile Include="Logic\StrippableTextTest.cs" />
<Compile Include="Logic\TimeCodeTest.cs" />
<Compile Include="Logic\VideoFormats\MatroskaTest.cs" />
<Compile Include="Logic\VobSub\VobSubTest.cs" />