From 1a542972c4098ac24ae13740e2fd645400152bac Mon Sep 17 00:00:00 2001
From: Daniel Schuette <d.schuette@online.de>
Date: Sat, 15 Sep 2018 19:39:01 -0400
Subject: [PATCH] bug fix - last enzyme in *.re file did not get parsed

---
 parse.go        | 13 +++++++++++--
 parse_test.go   | 30 ++++++++++++++++++------------
 tests/parse2.re |  2 +-
 tests/parse3.re |  1 +
 4 files changed, 31 insertions(+), 15 deletions(-)

diff --git a/parse.go b/parse.go
index ed9bb38..960b756 100644
--- a/parse.go
+++ b/parse.go
@@ -57,7 +57,16 @@ func ParseEnzymesFromFile(file string) (map[string]RestrictEnzyme, error) {
 
 Loop:
 	for i, n := 0, len(b); i < n; i++ {
-		// decide what to do next
+		// current char is the last char in the document => add parsed results to `enzymesMap'
+		if (i + 1) == n {
+			if itemContainer != nil {
+				if _, ok := enzymesMap[itemContainer.Name]; !ok {
+					enzymesMap[itemContainer.Name] = *itemContainer
+				}
+			}
+		}
+
+		// otherwise, the document is not yet fully parsed => decide what to do next
 		if i < len(b)-2 {
 			// if current char is a new line delimiter, decide how to proceed
 			if b[i] == '\n' {
@@ -126,7 +135,7 @@ Loop:
 		}
 	}
 
-	fmt.Printf("parsed %d enzymes from '%s'\n", line, file)
+	fmt.Printf("parsed %d of %d enzyme(s) from '%s'\n", len(enzymesMap), line, file)
 	return enzymesMap, nil
 }
 
diff --git a/parse_test.go b/parse_test.go
index 52a3748..84d0de1 100644
--- a/parse_test.go
+++ b/parse_test.go
@@ -2,6 +2,7 @@ package cloningprimer
 
 import (
 	"errors"
+	"log"
 	"testing"
 )
 
@@ -37,10 +38,10 @@ func TestParseEnzymesFromFile(t *testing.T) {
 			want: map[string]RestrictEnzyme{
 				"AclI": {
 					Name:            "AclI",
-					RecognitionSite: "aslkfhsdf",
-					NoPalinCleav:    "sdlfkj",
-					ID:              "sldkfj",
-					Isoschizomeres:  []string{"sdfklj", "sdlfkj"},
+					RecognitionSite: "invalid",
+					NoPalinCleav:    "invalid",
+					ID:              "invalid",
+					Isoschizomeres:  []string{"invalid", "invalid"},
 				},
 			},
 			err: nil,
@@ -51,10 +52,10 @@ func TestParseEnzymesFromFile(t *testing.T) {
 			want: map[string]RestrictEnzyme{
 				"AclI": {
 					Name:            "AclI",
-					RecognitionSite: "aslkfhsdf",
-					NoPalinCleav:    "sdlfkj",
-					ID:              "sdfk",
-					Isoschizomeres:  []string{"sdlkfj", "sdflkj"},
+					RecognitionSite: "invalid",
+					NoPalinCleav:    "invalid",
+					ID:              "invalid",
+					Isoschizomeres:  []string{"invalid", "invalid"},
 				},
 			},
 			err: nil,
@@ -65,10 +66,10 @@ func TestParseEnzymesFromFile(t *testing.T) {
 			want: map[string]RestrictEnzyme{
 				"AclI": {
 					Name:            "AclI",
-					RecognitionSite: "slfkj",
-					NoPalinCleav:    "sdlkfj",
-					ID:              "sldkfj",
-					Isoschizomeres:  []string{"sldkjf"},
+					RecognitionSite: "invalid",
+					NoPalinCleav:    "invalid",
+					ID:              "invalid",
+					Isoschizomeres:  []string{"invalid", "invalid"},
 				},
 			},
 			err: nil,
@@ -78,6 +79,8 @@ func TestParseEnzymesFromFile(t *testing.T) {
 	// loop over test cases
 	for _, c := range cases {
 		got, err := ParseEnzymesFromFile(c.in)
+		log.Printf("parsed len: %v, expect len: %v\n", len(got), len(c.want))
+		log.Printf("parsed: %v, expect: %v\n", got, c.want)
 
 		// test similarity of expected and received value
 		if !isSimilarMap(got, c.want) {
@@ -178,6 +181,9 @@ func isSimilarMap(m1, m2 map[string]RestrictEnzyme) bool {
 	if (m1 == nil) && (m2 == nil) {
 		return true
 	}
+	if (m1 == nil) || (m2 == nil) {
+		return false
+	}
 	for k, v := range m1 {
 		// test fields of type string
 		if val, ok := m2[k]; !ok {
diff --git a/tests/parse2.re b/tests/parse2.re
index f5f5d58..4f516bb 100644
--- a/tests/parse2.re
+++ b/tests/parse2.re
@@ -4,4 +4,4 @@
  * a parsed without a problem
  */
 enzyme_name       recognition_sequence                  non_palindromic_cleaveage   PDB_ID  isoschizomers
-'AclI'            'AACGTT'                              'no'
+'AclI'            'AACGTT'                              'no'                        'A1A1'  'AclI'
diff --git a/tests/parse3.re b/tests/parse3.re
index e3f5a7f..3889bb2 100644
--- a/tests/parse3.re
+++ b/tests/parse3.re
@@ -4,3 +4,4 @@
  * a parsed without a problem; even without column labels!
  */
 'AclI'            'AACGTT'                  'no'    'A1A1'  'AclI'
+'AclII'           'ACCGGT'                  'no'    'A2A2'  'AclII'