/[drupal]/contributions/modules/legislature/imports/ia/legis_bills.inc

Diff of /contributions/modules/legislature/imports/ia/legis_bills.inc

Parent Directory | Revision Log | View Revision Graph Revision Graph | View Patch Patch

-revision 1.7,
Thu Oct 30 03:21:49 2008 UTC
+revision 1.8,
Thu Jan  1 00:56:19 2009 UTC
 Line 1
  <?php
- // $Id: legis_bills.inc,v 1.6 2008/01/17 20:38:24 drumm Exp $
+ // $Id: legis_bills.inc,v 1.7 2008/10/30 03:21:49 drumm Exp $
  function legislature_ia_bills() {
    set_time_limit(0);
 Line 157 
 function legislature_ia_bill_history($ht
    // Start parsing <tr> tags and creating bill history array where an element = Date, Event description
    $data['actions'] = array();
    foreach ($xml->body->table[1]->tr as $row) {
-     $action = array (
+     $action = array(
        'date' => date_parse(preg_replace('/\s+/', ' ', $row->td[0]->font)),
        'description' => trim(preg_replace('/<[^>]*>([^<.,]*).*/', '\1', preg_replace('/\s+/', ' ', $row->td[1]->font->asXML()))),
        'motion' => preg_replace('/\s+/', ' ', strip_tags($row->td[1]->font->asXML())),
 Line 184 
 function legislature_ia_bill_history($ht
        $action['outcome'] = $passed[$matches[1]];
        $action['ayes'] = $matches[3];
        $action['noes'] = $matches[4];
+       $journal = drupal_http_request(preg_replace('/#.*/', '', $row->td[1]->font->a['href']));
+       $result_string = legislature_pdf2string($journal->data);
+       $votes = array(
+         'Yeas'    => NULL,
+         'Nays'    => NULL,
+         'Present' => NULL,
+         'Absent'  => NULL,
+       );
+       $measure = str_replace(array('HF', 'SF'), array('H.F.', 'S.F.'), $bill['measure']);
+       // Extract text lines after the S.F bill number to ensure we get
+       // the lines that correspond to the correct bill number
+       $entries = array();
+       foreach (explode('On the question', $result_string) as $entry) {
+         if (preg_match("/\(". $measure ."\)/", $entry) == 1) {
+           array_push($entries, $entry);
+         }
+       }
+       // Extract text lines based on 2 conditions, we've seen "Shall the bill pass" and S.F. (bill number)
+       foreach($entries as $value) {
+         if (preg_match("/Shall the bill pass?/", $value) == 1 && preg_match('/'. $measure .'/', $value) == 1) {
+           $split_result_string_on_the_bill = explode("The bill", $value);
+         }
+       }
+       $unformatted_text = $split_result_string_on_the_bill[0];
+       $unformatted_text = preg_replace("/\d+ JOURNAL OF THE SENATE .* Day /", "", $unformatted_text);
+       // This section attempts to format the vote text for easy parsing
+       // Use # as a way to easily split the string
+       $unformatted_text = substr($unformatted_text, strpos($unformatted_text, ':') + 1);
+       $unformatted_text = str_replace(', none', ', 0: none', $unformatted_text);
+       $unformatted_text = str_replace('.', '', $unformatted_text);
+       $unformatted_text = str_replace('Yeas', '#Yeas', $unformatted_text);
+       $unformatted_text = str_replace('Nays', '#Nays', $unformatted_text);
+       $unformatted_text = str_replace('Present', '#Present', $unformatted_text);
+       $unformatted_text = str_replace('Absent', '#Absent', $unformatted_text);
+       foreach(explode('#', $unformatted_text) as $position) {
+         if (!empty($position)) {
+           $pos_array = explode(':', $position);
+           $pos_vote_count = explode(',', $pos_array[0]);
+           $pos_names = explode(' ', $pos_array[1]);
+           $pos_count = trim($pos_vote_count[1]);
+           if ($pos_count != '0') {
+             $cleaned_names = array();
+             for ($i=0; $i < count($pos_names); $i += 1) {
+               if (preg_match("/\d/",$pos_names[$i])==1){
+                 $i += 6;
+               }
+               elseif (!empty($pos_names[$i])) {
+                 array_push($cleaned_names, $pos_names[$i]);
+               }
+             }
+             $votes[$pos_vote_count[0]] = $cleaned_names;
+           }
+         }
+       }
+       dpr($votes);
+       $data['actions'][] = $action;
      }
+   }
+ }
-     // todo figure out bill status
+ /**
+  * Convert pdf to plain text.
+  *
+  * @param $content
+  *   PDF document
+  * @return
+  *   Plain text of pdf with the position of the string set to beginning.
+  */
+ function legislature_pdf2string($content) {
+   $searchstart = 'stream';
+   $searchend = 'endstream';
+   $pdfText = '';
+   $pos = 0;
+   $pos2 = 0;
+   $startpos = 0;
+   while ($pos !== FALSE && $pos2 !== FALSE) {
+     $pos = strpos($content, $searchstart, $startpos);
+     $pos2 = strpos($content, $searchend, $startpos + 1);
+     if ($pos !== FALSE && $pos2 !== FALSE){
+       if ($content[$pos] == 0x0d && $content[$pos + 1] == 0x0a) {
+         $pos += 2;
+       }
+       elseif ($content[$pos] == 0x0a) {
+         $pos += 1;
+       }
-     $data['actions'][] = $action;
+       if ($content[$pos2 - 2] == 0x0d && $content[$pos2 - 1] == 0x0a) {
+         $pos2 -= 2;
+       }
+       elseif ($content[$pos2 - 1] == 0x0a) {
+         $pos2 -= 1;
+       }
+       $textsection = substr($content, $pos + strlen($searchstart) + 2, $pos2 - $pos - strlen($searchstart) - 1);
+       $data = @gzuncompress($textsection);
+       $pdfText .= legislature_pdf_extract_text($data);
+       $startpos = $pos2 + strlen($searchend) - 1;
+     }
    }
-   /*
+   return preg_replace('/(\s)+/', ' ', $pdfText);
-   // We re-parse the page here to get the link(s) associated with a given entry
+ }
-   // Each the link goes to a senate journal in pdf form. The links contain
-   // spaces which are escaped for parsing
+ /**
-   // todo merge into upper loop
+  * Used for pdf conversion.
-   // todo go ahead and get votes
+  *
-   $parser = new HtmlParser($html_page);
+  * @param $psData
-   $links = get_all_links_after_hr_tag($parser);
+  *   Uncompressed data.
-   $links = create_escaped_links($links);
+  * @return
+  *   Plain text of pdf.
-   // Append link(s) to given bill history entry
+  */
-   for ( $i = 0; $i < count($bill_history); $i += 1) {
+ function legislature_pdf_extract_text($psData){
-     array_push($bill_history[$i]["journal_links"], $links[$i]);
+   if (!is_string($psData)) {
+     return '';
    }
-   */
+   $text = '';
+   // Handle brackets in the text stream that could be mistaken for the end of a
+   // text field. I'm sure you can do this as part of the regular expression,
+   // but my skills aren't good enough yet.
+   $psData = str_replace('\)', '##ENDBRACKET##', $psData);
+   $psData = str_replace('\]', '##ENDSBRACKET##', $psData);
+   preg_match_all('/(T[wdcm*])[\s]*(\[([^\]]*)\]|\(([^\)]*)\))[\s]*Tj/si', $psData, $matches);
+   for ($i = 0; $i < sizeof($matches[0]); $i += 1) {
+     if ($matches[3][$i] != '') {
+       // Run another match over the contents.
+       preg_match_all('/\(([^)]*)\)/si', $matches[3][$i], $subMatches);
+       foreach ($subMatches[1] as $subMatch) {
+         $text .= $subMatch;
+       }
+     } else if ($matches[4][$i] != '') {
+       $text .= ($matches[1][$i] == 'Tc' ? ' ' : '') . $matches[4][$i];
+     }
+   }
+   // Translate special characters and put back brackets.
+   $trans = array(
+     '...'                => '…',
+     '\205'                => '…',
+     '\221'                => chr(145),
+     '\222'                => chr(146),
+     '\223'                => chr(147),
+     '\224'                => chr(148),
+     '\226'                => '-',
+     '\267'                => '•',
+     '\('                => '(',
+     '\['                => '[',
+     '##ENDBRACKET##'    => ')',
+     '##ENDSBRACKET##'    => ']',
+     chr(133)            => '-',
+     chr(141)            => chr(147),
+     chr(142)            => chr(148),
+     chr(143)            => chr(145),
+     chr(144)            => chr(146),
+   );
+   return strtr($text, $trans);
  }

 Legend:



Removed from v.1.7
 


changed lines


 
Added in v.1.8
 Legend:



Removed from v.1.7
 


changed lines


 
Added in v.1.8
-Removed from v.1.7
+Added in v.1.8

	ViewVC Help
Powered by ViewVC 1.1.2