github
/
notepad-plus-plus
mirror of https://github.com/notepad-plus-plus/notepad-plus-plus
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Fix file content detection for xml/html/php/bash

Browse Source 
Add the ability of take into account Unicode BOM for file content
detection (xml/html/php/bash).
pull/1022/head
Don Ho 9 years ago
parent 2cbc6a7a99
commit 2c80fc3018
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File

13
PowerEditor/src/ScitillaComponent/Buffer.cpp
Unescape View File

@ -1261,9 +1261,20 @@ LangType FileManager::detectLanguageFromTextBegining(const unsigned char *data,
std::string htmlHeader2 = "<html>"; // length : 6 std::string htmlHeader2 = "<html>"; // length : 6
std::string htmlHeader1 = "<!DOCTYPE html>"; // length : 15 std::string htmlHeader1 = "<!DOCTYPE html>"; // length : 15
const size_t longestLength = htmlHeader1.length(); // longest length - html header Length const size_t longestLength = htmlHeader1.length(); // longest length : html header Length
const size_t shortestLength = xmlHeader.length();
size_t i = 0; size_t i = 0;
if (dataLen <= shortestLength)
return L_TEXT;
// Eliminate BOM if present
if ((data[0] == 0xEF && data[1] == 0xBB && data[2] == 0xBF) || // UTF8 BOM
(data[0] == 0xFE && data[1] == 0xFF && data[2] == 0x00) || // UTF16 BE BOM
(data[0] == 0xFF && data[1] == 0xFE && data[2] == 0x00)) // UTF16 LE BOM
i += 3;
for (; i < dataLen; ++i) for (; i < dataLen; ++i)
{ {
if (data[i] != ' ' && data[i] != '\t' && data[i] != '\n' && data[i] != '\r') if (data[i] != ' ' && data[i] != '\t' && data[i] != '\n' && data[i] != '\r')

Write Preview
Loading…
Cancel
Save