Index: parser_csv_parser.inc
===================================================================
RCS file: /cvs/drupal-contrib/contributions/modules/parser_csv/Attic/parser_csv_parser.inc,v
retrieving revision 1.1.2.3
diff -u -p -r1.1.2.3 parser_csv_parser.inc
--- parser_csv_parser.inc	23 Jan 2009 19:38:26 -0000	1.1.2.3
+++ parser_csv_parser.inc	18 Feb 2009 13:29:26 -0000
@@ -52,128 +52,223 @@ class ParserCSVIterator implements Itera
 }
 
 /**
- * Parse CSV files into a two dimensional array.
- * @todo: accept a timeout parameter for partial parsing. 
- * 
- * @param Iterator $lineIterator
- *   File iterator that implements Iterator. E. g. ParserCSVIterator
- * @return 
- *   Two dimensional array that contains the data in the CSV file.
+ * Functionality to parse CSV files into a two dimensional array.
  */
-function parser_csv_parse(Iterator $lineIterator, $delimiter = ',', $skipLine = FALSE) {
-  $rows = array();
-  for ($lineIterator->rewind(); $lineIterator->valid(); $lineIterator->next()) {
-    // Make really sure we've got lines without trailing newlines.
-    $line = trim($lineIterator->current(), "\r\n");
-
-    // Skip empty lines.
-    if (empty($line)) {
-      continue;
-    }
-    // If the first line contains column names, skip it.
-    if ($skipLine) {
-      $skipLine = FALSE;
-      continue;
-    }
+class ParserCSV {
+  private $delimiter;
+  private $skipFirstLine;
+  private $columnNames;
+  private $timeout;
+  private $timeoutReached;
+
+  public function __construct() {
+    $this->delimiter = ',';
+    $this->skipFirstLine = FALSE;
+    $this->columnNames = FALSE;
+    $this->timeout = FALSE;
+    $this->timeoutReached = FALSE;
+  }
 
-    // The actual parser. explode() is unfortunately not suitable because the
-    // delimiter might be located inside a quoted field, and that would break
-    // the field and/or require additional effort to re-join the fields.
-    $quoted = FALSE;
-    $currentIndex = 0;
-    $currentField = '';
-    $fields = array();
-
-    while ($currentIndex <= strlen($line)) {
-      if ($quoted) {
-        $nextQuoteIndex = strpos($line, '"', $currentIndex);
-
-        if ($nextQuoteIndex === FALSE) {
-          // There's a line break before the quote is closed, so fetch the
-          // next line and start from there.
-          $currentField .= substr($line, $currentIndex);
-          $lineIterator->next();
-
-          if (!$lineIterator->valid()) {
-            // Whoa, an unclosed quote! Well whatever, let's just ignore
-            // that shortcoming and record it nevertheless.
-            $fields[] = $currentField;
-            break;
-          }
-          // Ok, so, on with fetching the next line, as mentioned above.
-          $currentField .= "\n";
-          $line = trim($lineIterator->current(), "\r\n");
-          $currentIndex = 0;
-          continue;
-        }
+  /**
+   * Set the column delimiter string.
+   * By default, the comma (',') is used as delimiter.
+   */
+  public function setDelimiter($delimiter) {
+    $this->delimiter = ',';
+  }
 
-        // There's actually another quote in this line...
-        // find out whether it's escaped or not.
-        $currentField .= substr($line, $currentIndex, $nextQuoteIndex - $currentIndex);
-
-        if ($line[$nextQuoteIndex + 1] === '"') {
-          // Escaped quote, add a single one to the field and proceed quoted.
-          $currentField .= '"';
-          $currentIndex = $nextQuoteIndex + 2;
-        }
-        else {
-          // End of the quoted section, close the quote and let the
-          // $quoted == FALSE block finalize the field.
-          $quoted = FALSE;
-          $currentIndex = $nextQuoteIndex + 1;
-        }
+  /**
+   * Set this to TRUE if the parser should skip the first line of the CSV text,
+   * which might be desired if the first line contains the column names.
+   * By default, this is set to FALSE and the first line is not skipped.
+   */
+  public function setSkipFirstLine($skipFirstLine) {
+    $this->skipFirstLine = $skipFirstLine;
+  }
+
+  /**
+   * Specify an array of column names if you know them in advance, or FALSE
+   * (which is the default) to unset any prior column names. If no column names
+   * are set, the parser will put each row into a simple numerically indexed
+   * array. If column names are given, the parser will create arrays with
+   * these column names as array keys instead.
+   */
+  public function setColumnNames($columnNames) {
+    $this->columnNames = $columnNames;
+  }
+
+  /**
+   * Define the time (in milliseconds) after which the parser stops parsing,
+   * even if it has not yet finished processing the CSV data. If the timeout
+   * has been reached before parsing is done, the parse() method will return
+   * an incomplete list of rows - a single row will never be cut off in the
+   * middle, though. By default, no timeout (@p $timeout == FALSE) is defined.
+   *
+   * You can check if the timeout has been reached by calling the
+   * timeoutReached() method after parse() has been called.
+   */
+  public function setTimeout($timeout) {
+    $this->timeout = $timeout;
+  }
+
+  /**
+   * After calling the parse() method, determine if the timeout (set by the
+   * setTimeout() method) has been reached.
+   */
+  public function timeoutReached() {
+    return $this->timeoutReached;
+  }
+
+  /**
+   * Parse CSV files into a two dimensional array.
+   *
+   * @param Iterator $lineIterator
+   *   An Iterator object that yields line strings, e.g. ParserCSVIterator.
+   * @return
+   *   Two dimensional array that contains the data in the CSV file.
+   */
+  public function parse(Iterator $lineIterator) {
+    $skipLine = $this->skipFirstLine;
+    $rows = array();
+
+    $this->timeoutReached = FALSE;
+    $maxTime = empty($this->timeout) ? FALSE : (microtime() + $this->timeout);
+
+    for ($lineIterator->rewind(); $lineIterator->valid(); $lineIterator->next()) {
+      // If the timeout has been reached, quit parsing even if we're not yet done.
+      if (!empty($maxTime) && microtime() > $maxTime) {
+        $this->timeoutReached = TRUE;
+        break;
       }
-      else { // $quoted == FALSE
-        // First, let's find out where the next character of interest is.
-        $nextQuoteIndex = strpos($line, '"', $currentIndex);
-        $nextDelimiterIndex = strpos($line, $delimiter, $currentIndex);
 
-        if ($nextQuoteIndex === FALSE) {
-          $nextIndex = $nextDelimiterIndex;
-        }
-        elseif ($nextDelimiterIndex === FALSE) {
-          $nextIndex = $nextQuoteIndex;
-        }
-        else {
-          $nextIndex = min($nextQuoteIndex, $nextDelimiterIndex);
-        }
+      // Make really sure we've got lines without trailing newlines.
+      $line = trim($lineIterator->current(), "\r\n");
 
-        if ($nextIndex === FALSE) {
-          // This line is done, add the rest of it as last field.
-          $currentField .= substr($line, $currentIndex);
-          $fields[] = $currentField;
-          break;
-        }
-        elseif ($line[$nextIndex] === $delimiter[0]) {
-          $length = ($nextIndex + strlen($delimiter) - 1) - $currentIndex;
-          $currentField .= substr($line, $currentIndex, $length);
-          $fields[] = $currentField;
-          $currentField = '';
-          $currentIndex += $length + 1;
-          // Continue with the next field.
+      // Skip empty lines.
+      if (empty($line)) {
+        continue;
+      }
+      // If the first line contains column names, skip it.
+      if ($skipLine) {
+        $skipLine = FALSE;
+        continue;
+      }
+
+      // The actual parser. explode() is unfortunately not suitable because the
+      // delimiter might be located inside a quoted field, and that would break
+      // the field and/or require additional effort to re-join the fields.
+      $quoted = FALSE;
+      $currentIndex = 0;
+      $currentField = '';
+      $fields = array();
+
+      while ($currentIndex <= strlen($line)) {
+        if ($quoted) {
+          $nextQuoteIndex = strpos($line, '"', $currentIndex);
+
+          if ($nextQuoteIndex === FALSE) {
+            // There's a line break before the quote is closed, so fetch the
+            // next line and start from there.
+            $currentField .= substr($line, $currentIndex);
+            $lineIterator->next();
+
+            if (!$lineIterator->valid()) {
+              // Whoa, an unclosed quote! Well whatever, let's just ignore
+              // that shortcoming and record it nevertheless.
+              $fields[] = $currentField;
+              break;
+            }
+            // Ok, so, on with fetching the next line, as mentioned above.
+            $currentField .= "\n";
+            $line = trim($lineIterator->current(), "\r\n");
+            $currentIndex = 0;
+            continue;
+          }
+
+          // There's actually another quote in this line...
+          // find out whether it's escaped or not.
+          $currentField .= substr($line, $currentIndex, $nextQuoteIndex - $currentIndex);
+
+          if (isset($line[$nextQuoteIndex + 1]) && $line[$nextQuoteIndex + 1] === '"') {
+            // Escaped quote, add a single one to the field and proceed quoted.
+            $currentField .= '"';
+            $currentIndex = $nextQuoteIndex + 2;
+          }
+          else {
+            // End of the quoted section, close the quote and let the
+            // $quoted == FALSE block finalize the field.
+            $quoted = FALSE;
+            $currentIndex = $nextQuoteIndex + 1;
+          }
         }
-        else { // $line[$nextIndex] == '"'
-          $quoted = TRUE;
-          $currentField .= substr($line, $currentIndex, $nextIndex - $currentIndex);
-          $currentIndex = $nextIndex + 1;
-          // Continue this field in the $quoted == TRUE block.
+        else { // $quoted == FALSE
+          // First, let's find out where the next character of interest is.
+          $nextQuoteIndex = strpos($line, '"', $currentIndex);
+          $nextDelimiterIndex = strpos($line, $this->delimiter, $currentIndex);
+
+          if ($nextQuoteIndex === FALSE) {
+            $nextIndex = $nextDelimiterIndex;
+          }
+          elseif ($nextDelimiterIndex === FALSE) {
+            $nextIndex = $nextQuoteIndex;
+          }
+          else {
+            $nextIndex = min($nextQuoteIndex, $nextDelimiterIndex);
+          }
+
+          if ($nextIndex === FALSE) {
+            // This line is done, add the rest of it as last field.
+            $currentField .= substr($line, $currentIndex);
+            $fields[] = $currentField;
+            break;
+          }
+          elseif ($line[$nextIndex] === $this->delimiter[0]) {
+            $length = ($nextIndex + strlen($this->delimiter) - 1) - $currentIndex;
+            $currentField .= substr($line, $currentIndex, $length);
+            $fields[] = $currentField;
+            $currentField = '';
+            $currentIndex += $length + 1;
+            // Continue with the next field.
+          }
+          else { // $line[$nextIndex] == '"'
+            $quoted = TRUE;
+            $currentField .= substr($line, $currentIndex, $nextIndex - $currentIndex);
+            $currentIndex = $nextIndex + 1;
+            // Continue this field in the $quoted == TRUE block.
+          }
         }
       }
-    }
-    // End of CSV parser. We've now got all the fields of the line as strings
-    // in the $fields array.
+      // End of CSV parser. We've now got all the fields of the line as strings
+      // in the $fields array.
 
-    if (empty($columnNames)) {
-      $row = $fields;
-    }
-    else {
-      $row = array();
-      foreach ($columnNames as $columnName) {
-        $field = array_shift($fields);
-        $row[$columnName] = isset($field) ? $field : '';
+      if (empty($this->columnNames)) {
+        $row = $fields;
       }
+      else {
+        $row = array();
+        foreach ($this->columnNames as $columnName) {
+          $field = array_shift($fields);
+          $row[$columnName] = isset($field) ? $field : '';
+        }
+      }
+      $rows[] = $row;
     }
-    $rows[] = $row;
+    return $rows;
   }
-  return $rows;
-}
\ No newline at end of file
+}
+
+/**
+ * Parse CSV files into a two dimensional array.
+ * (Convenience function for ParserCSV::parse().)
+ *
+ * @param Iterator $lineIterator
+ *   An Iterator object that yields line strings, e.g. ParserCSVIterator.
+ * @return
+ *   Two dimensional array that contains the data in the CSV file.
+ */
+function parser_csv_parse(Iterator $lineIterator, $delimiter = ',', $skipFirstLine = FALSE) {
+  $parser = new ParserCSV();
+  $parser->setDelimiter($delimiter);
+  $parser->setSkipFirstLine($skipFirstLine);
+  return $parser->parse($lineIterator);
+}