Add support for parsing duplicated segments

Prior to this change, mulitple identical segments could not be read. The
parser would always return null if duplicated segments were found.

This changes allows an offset to be passed, to specify reading a
repeated segment.

Author: johanib

src/EDI/Reader.php

@@ -174,10 +174,9 @@ public function readEdiDataValueReq($filter, int $l1, $l2 = false)
      * @param bool         $required  if required, but no exist, register error
      * @return string|null
      */
-    public function readEdiDataValue($filter, int $l1, $l2 = false, bool $required = false)
+    public function readEdiDataValue($filter, int $l1, $l2 = false, bool $required = false, int $offset = null)
     {
-        $segment = false;
-        $segment_count = 0;
+        $found_segments = [];
         $segment_name = $filter;
         $filter_elements = false;
         if (\is_array($filter)) {
@@ -221,24 +220,23 @@ public function readEdiDataValue($filter, int $l1, $l2 = false, bool $required =
                         continue;
                     }
                 }
-                $segment = $edi_row;
-                $segment_count++;
+                $found_segments[] = $edi_row;
             }
         }
 
-        // no segment found
-        if (! $segment) {
-            if ($required) {
-                $this->errors[] = 'Segment "'.$segment_name.'" no exist';
+        try {
+            if ($offset !== null) {
+                $segment = $this->getOffsetSegmentFromResult($found_segments, $offset, $required, $segment_name);
+            } else {
+                $segment = $this->getSegmentFromResult($found_segments, $required, $segment_name);
             }
+        } catch (ReaderException $e) {
+            $this->errors[] = $e->getMessage();
 
             return null;
         }
 
-        // found more than one segment - error
-        if ($segment_count > 1) {
-            $this->errors[] = 'Segment "'.$segment_name.'" is ambiguous';
-
+        if ($segment === false) {
             return null;
         }
 
@@ -561,4 +559,45 @@ private static function unwrap($string)
             }
         }
     }
+
+    /**
+     * @param array $matchingSegments
+     * @param int   $offset
+     * @param bool  $required
+     * @param mixed $segment_name
+     *
+     * @return false|mixed
+     */
+    private function getOffsetSegmentFromResult(array $matchingSegments, int $offset, bool $required, mixed $segment_name): mixed
+    {
+        if (isset($matchingSegments[$offset])) {
+            return $matchingSegments[$offset];
+        }
+
+        if ($required) {
+            throw new ReaderException('Segment "' . $segment_name . '" does not exist at offset "' . $offset . '"');
+        }
+
+        return false;
+    }
+
+    /**
+     * @param array $matchingSegments
+     * @param mixed $segment_name
+     *
+     * @return false|mixed
+     */
+    private function getSegmentFromResult(array $matchingSegments, bool $required, mixed $segment_name): mixed
+    {
+        // found more than one segment - error
+        if (count($matchingSegments) > 1) {
+            throw new ReaderException('Segment "' . $segment_name . '" is ambiguous');
+        }
+
+        if ($required && !isset($matchingSegments[0])) {
+            throw new ReaderException('Segment "' . $segment_name . '" no exist');
+        }
+
+        return $matchingSegments[0] ?? false;
+    }
 }

src/EDI/ReaderException.php

@@ -0,0 +1,11 @@
+<?php
+
+declare(strict_types=1);
+
+namespace EDI;
+
+use RuntimeException;
+
+class ReaderException extends RuntimeException
+{
+}

tests/EDITest/ReaderTest.php

@@ -4,8 +4,8 @@
 
 namespace EDITest;
 
-use EDI\Reader;
 use EDI\Parser;
+use EDI\Reader;
 
 /**
  * @internal
@@ -102,4 +102,47 @@ public function testSplitMultiMessage()
         $messageType = $r->readUNHmessageType();
         static::assertSame('PAORES', $messageType);
     }
+
+    public function testReadsMultiSegmentsByOffset()
+    {
+        $p = new Parser();
+        $p->setStrict(true);
+        $p->load(__DIR__ . '/../files/example_multiline.edi');
+        $r = new Reader($p);
+
+        $lines = [];
+        for ($i = 0; $i < 10; $i++) {
+            $line = $r->readEdiDataValue(['FTX', [1 => 'AAI']], 4, false, false, $i);
+            if ($line !== null) {
+                $lines[] = $line;
+            }
+        }
+
+        self::assertSame(
+            [
+                0 => [
+                    0 => 'PLS ENSURE TO TAKE OUR APPROVAL PRIOR STUFFING ANY NON HAZ CHEMICA',
+                    1 => 'LS',
+                ],
+                1 => [
+                    0 => 'THE SHIPPER SHALL NOT BE RESPONSIBLE FOR ANY COSTS/DELAYS OCCUR',
+                    1 => 'DUE TO INTERVENTION OF CUSTOMS.',
+                ],
+
+            ],
+            $lines
+        );
+    }
+
+    public function testAddsErrorOnMissingRequiredOffest()
+    {
+        $p = new Parser();
+        $p->setStrict(true);
+        $p->load(__DIR__ . '/../files/example_multiline.edi');
+        $r = new Reader($p);
+        $line = $r->readEdiDataValue(['FTX', [1 => 'AAI']], 4, false, true, 99);
+        self::assertSame(['Segment "FTX" does not exist at offset "99"'], $r->errors());
+        self::assertNull($line);
+    }
+
 }

tests/files/example_multiline.edi

@@ -0,0 +1,10 @@
+UNB+UNOB:2+CARRIER+RECEIVER-ID+999818:999+251'
+UNH+0001+IFTMBC:D:00B:UN'
+BGM+770+AAA99970929+9'
+TSR+30+2:::2'
+FTX+AAI+++PLS ENSURE TO TAKE OUR APPROVAL PRIOR STUFFING ANY NON HAZ CHEMICA:LS'
+FTX+ABV+++THIS BOOKING CONFIRMATION IS SUBJECT TO SEALING'
+FTX+AAI+++THE SHIPPER SHALL NOT BE RESPONSIBLE FOR ANY COSTS/DELAYS OCCUR
+:DUE TO INTERVENTION OF CUSTOMS.'
+UNT+10+0001'
+UNZ+1+251'