Add basic test

iipc · Apr 3, 2019 · 3314290e864692df7a250f75bb68e8ba6f45e1d6 · 3314290
1 parent f77587b
commit 3314290e864692df7a250f75bb68e8ba6f45e1d6
diff --git a/pom.xml b/pom.xml
@@ -13,6 +13,11 @@
                <directory>${basedir}/resources</directory>
            </resource>
        </resources>
+  
+        <testResources>
+  
+            <testResource>
+  
+                <directory>${basedir}/test-resources</directory>
+  
+            </testResource>
+  
+        </testResources>
    </build>
    <properties>
@@ -38,5 +43,11 @@
            <artifactId>jackson-databind</artifactId>
            <version>2.9.8</version>
        </dependency>
+  
+        <dependency>
+  
+            <groupId>org.slf4j</groupId>
+  
+            <artifactId>slf4j-simple</artifactId>
+  
+            <version>1.7.25</version>
+  
+            <scope>test</scope>
+  
+        </dependency>
    </dependencies>
 </project>
diff --git a/src/org/netpreserve/logtrix/CrawlLogIterator.java b/src/org/netpreserve/logtrix/CrawlLogIterator.java
@@ -22,12 +22,13 @@
 */
 package org.netpreserve.logtrix;
-  
-import com.fasterxml.jackson.databind.JsonNode;
 import com.fasterxml.jackson.databind.ObjectMapper;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import java.io.*;
+  
+import java.nio.file.Files;
+  
+import java.nio.file.Path;
 import java.text.ParseException;
 import java.text.SimpleDateFormat;
 import java.util.Iterator;
@@ -70,19 +71,26 @@
     */
    CrawlDataItem next;
-  
-    String crawlLog;
-  
-
-  
-    /** 
+  
+    /**
     * Create a new CrawlLogIterator that reads items from a Heritrix crawl.log
     *
-  
-     * @param crawlLog The path of a Heritrix crawl.log file.
+  
+     * @param path The path of a Heritrix crawl.log file.
     * @throws IOException If errors were found reading the log.
     */
-  
-    public CrawlLogIterator(String crawlLog) 
-  
-            throws IOException {
-  
-    	this.crawlLog = crawlLog;
-  
-        in = new BufferedReader(new InputStreamReader(
-  
-                new FileInputStream(new File(crawlLog))));
+  
+    public CrawlLogIterator(Path path) throws IOException {
+  
+        this(Files.newBufferedReader(path));
+  
+    }
+  
+
+  
+    public CrawlLogIterator(Reader reader) {
+  
+        if (reader instanceof BufferedReader) {
+  
+            in = (BufferedReader) reader;
+  
+        } else {
+  
+            in = new BufferedReader(reader);
+  
+        }
+  
+    }
+  
+
+  
+    public CrawlLogIterator(InputStream stream) {
+  
+        this(new InputStreamReader(stream));
    }
    /** 

diff --git a/src/org/netpreserve/logtrix/CrawlSummary.java b/src/org/netpreserve/logtrix/CrawlSummary.java
@@ -0,0 +1,7 @@
+  
+package org.netpreserve.logtrix;
+  
+
+  
+public class CrawlSummary {
+  
+    // server errors
+  
+    //
+  
+
+  
+}
diff --git a/test-resources/org/netpreserve/logtrix/crawl.log b/test-resources/org/netpreserve/logtrix/crawl.log
@@ -0,0 +1,10 @@
+  
+2019-04-03T11:15:34.547Z     1         60 dns:www.nla.gov.au P https://www.nla.gov.au/ text/dns #005 20190403111533835+88 sha1:IX3XBWGMPE6YHAI23RZ5WOQW7LUVTWRL - -
+  
+2019-04-03T11:15:34.547Z     1         58 dns:trove.nla.gov.au P https://trove.nla.gov.au/ text/dns #013 20190403111533835+88 sha1:TZB2ZJIYG2JCXCEEMLQBZBRPB7O5HLLQ - -
+  
+2019-04-03T11:15:40.735Z   200       2419 https://www.nla.gov.au/robots.txt P https://www.nla.gov.au/ text/plain #013 20190403111537663+3009 sha1:5EPWKI3UTXDMSJAHMIJ5K7GG6IWCEYVR - -
+  
+2019-04-03T11:15:40.787Z   200        868 https://trove.nla.gov.au/robots.txt P https://trove.nla.gov.au/ text/plain #005 20190403111537654+3115 sha1:FLYK3OSFKQFJ22QCRE3H4UPGFOECPR2O - -
+  
+2019-04-03T11:15:59.643Z   200      12762 https://trove.nla.gov.au/ - - text/html #013 20190403111556775+2163 sha1:EVIOANLOBTQAZPYDTGHBQYBX5XXUBTP3 - 3t
+  
+2019-04-03T11:15:59.694Z     1         75 dns:www.google-analytics.com XP https://www.google-analytics.com/analytics.js text/dns #013 20190403111559676+17 sha1:SA7KKTX67KHOBFILMIP27NTZNEBNIE3U - -
+  
+2019-04-03T11:16:00.307Z   200      84465 https://www.nla.gov.au/ - - text/html #002 20190403111555799+3021 sha1:ZDZH7LRCOUX6EGLPBFCCKCN6A7PNJKJ6 - 3t
+  
+2019-04-03T11:16:00.334Z     1        602 dns:www.youtube.com XP https://www.youtube.com/ text/dns #002 20190403111600320+7 sha1:4WP3UVEOLDANMWNWQ3QWI7VANPP5NY3U - -
+  
+2019-04-03T11:16:00.383Z     1        379 dns:static.hotjar.com XP https://static.hotjar.com/c/hotjar- text/dns #002 20190403111600340+42 sha1:F3KO34UV4D25BZXTB3ZME2HOGBAR7TIA - -
+  
+2019-04-03T11:16:02.897Z   200         78 https://www.google-analytics.com/robots.txt XP https://www.google-analytics.com/analytics.js text/plain #013 20190403111602703+190 sha1:BXF7TB66SUXCQHKMMDI3JX7XUVMMRTWM - -
diff --git a/test/org.netpreserve.logtrix/CrawlLogIteratorTest.java b/test/org.netpreserve.logtrix/CrawlLogIteratorTest.java
@@ -1,13 +1,16 @@
 package org.netpreserve.logtrix;
+  
+import org.junit.Test;
+  
+
 import java.io.IOException;
 import static org.junit.Assert.*;
 public class CrawlLogIteratorTest {
+  
+    @Test
    public void test() throws IOException {
-  
-        try (CrawlLogIterator log = new CrawlLogIterator("crawl.log")) {
+  
+        try (CrawlLogIterator log = new CrawlLogIterator(getClass().getResourceAsStream("crawl.log"))) {
            for (CrawlDataItem item: log) {
                System.out.println(item.getURL());
            }