首页 / 网页编程 / PHP / php删除文本文件中重复行的方法

/** * RemoveDuplicatedLines * This function removes all duplicated lines of the given text file. * * @param string * @param bool * @returnstring */function RemoveDuplicatedLines（$Filepath, $IgnoreCase=false, $NewLine="
"）{if （！file_exists（$Filepath））{$ErrorMsg = "RemoveDuplicatedLines error: ";$ErrorMsg .= "The given file " . $Filepath . " does not exist！";die（$ErrorMsg）;}$Content = file_get_contents（$Filepath）;$Content = RemoveDuplicatedLinesByString（$Content, $IgnoreCase, $NewLine）;// Is the file writeable?if （！is_writeable（$Filepath））{$ErrorMsg = "RemoveDuplicatedLines error: ";$ErrorMsg .= "The given file " . $Filepath . " is not writeable！";die（$ErrorMsg）;}// Write the new file$FileResource = fopen（$Filepath, "w+"）; fwrite（$FileResource, $Content）;fclose（$FileResource）;} /** * RemoveDuplicatedLinesByString * This function removes all duplicated lines of the given string. * * @param string * @param bool * @returnstring */function RemoveDuplicatedLinesByString（$Lines, $IgnoreCase=false, $NewLine="
"）{if （is_array（$Lines））$Lines = implode（$NewLine, $Lines）;$Lines = explode（$NewLine, $Lines）;$LineArray = array（）;$Duplicates = 0;// Go trough all lines of the given filefor （$Line=0; $Line < count（$Lines）; $Line++）{// Trim whitespace for the current line$CurrentLine = trim（$Lines[$Line]）;// Skip empty linesif （$CurrentLine == ""）continue;// Use the line contents as array key$LineKey = $CurrentLine;if （$IgnoreCase）$LineKey = strtolower（$LineKey）;// Check if the array key already exists,// if not add it otherwise increase the counterif （！isset（$LineArray[$LineKey]））$LineArray[$LineKey] = $CurrentLine;else$Duplicates++;}// Sort the arrayasort（$LineArray）;// Return how many lines got removedreturn implode（$NewLine, array_values（$LineArray））;}

// Example 1// Removes all duplicated lines of the file definied in the first parameter.$RemovedLinesCount = RemoveDuplicatedLines（"test.txt"）;print "Removed $RemovedLinesCount duplicate lines from the test.txt file.";// Example 2 （Ignore case）// Same as above, just ignores the line case.RemoveDuplicatedLines（"test.txt", true）;// Example 3 （Custom new line character）// By using the 3rd parameter you can define which character// should be used as new line indicator. In this case// the example file looks like "foo;bar;foo;foo" and will// be replaced with "foo;bar" RemoveDuplicatedLines（"test.txt", false, ";"）;