Merge pull request apache#437 from sebastian-nagel/NUTCH-2693-misspel…

…led-properties

NUTCH-2693 Misspelled configuration property names in documentation

conf/nutch-default.xml

@@ -849,14 +849,14 @@
   <value>-1</value>
   <description>The maximum number of urls in a single
   fetchlist.  -1 if unlimited. The urls are counted according
-  to the value of the parameter generator.count.mode.
+  to the value of the parameter generate.count.mode.
   </description>
 </property>
 
 <property>
   <name>generate.count.mode</name>
   <value>host</value>
-  <description>Determines how the URLs are counted for generator.max.count.
+  <description>Determines how the URLs are counted for generate.max.count.
   Default value is 'host' but can be 'domain'. Note that we do not count 
   per IP in the new version of the Generator.
   </description>
@@ -1062,7 +1062,7 @@
 <property>
   <name>fetcher.throughput.threshold.retries</name>
   <value>5</value>
-  <description>The number of times the fetcher.throughput.threshold is allowed to be exceeded.
+  <description>The number of times the fetcher.throughput.threshold.pages is allowed to be exceeded.
   This settings prevents accidental slow downs from immediately killing the fetcher thread.
   </description>
 </property>

src/java/org/apache/nutch/crawl/Generator.java

@@ -702,9 +702,9 @@ public Path[] generate(Path dbDir, Path segments, int numLists, long topN,
 
   /**
    * Generate fetchlists in one or more segments. Whether to filter URLs or not
-   * is read from the crawl.generate.filter property in the configuration files.
-   * If the property is not found, the URLs are filtered. Same for the
-   * normalisation.
+   * is read from the "generate.filter" property set for the job from
+   * command-line. If the property is not found, the URLs are filtered. Same for
+   * the normalisation.
    * 
    * @param dbDir
    *          Crawl database directory

src/java/org/apache/nutch/net/protocols/Response.java

@@ -62,7 +62,7 @@ public static enum TruncatedContentReason {
     NOT_TRUNCATED,
     /** fetch exceeded configured http.content.limit */
     LENGTH,
-    /** fetch exceeded configured http.fetch.duration */
+    /** fetch exceeded configured http.time.limit */
     TIME,
     /** network disconnect or timeout during fetch */
     DISCONNECT,

src/plugin/indexer-csv/src/java/org/apache/nutch/indexwriter/csv/CSVIndexWriter.java

@@ -393,7 +393,7 @@ private void writeQuoted (String value) throws IOException {
 
   /**
    * Write a value to output stream. Escape quote characters.
-   * Clip value after <code>indexer.csv.maxfieldlength</code> characters.
+   * Clip value after <code>maxfieldlength</code> characters.
    *
    * @param value
    *          String to write
@@ -419,7 +419,7 @@ private void writeEscaped (String value, int nextQuoteChar) throws IOException {
 
   /**
    * Write a value to output stream. Escape quote characters. Clip value after
-   * <code>indexer.csv.maxfieldlength</code> characters.
+   * <code>maxfieldlength</code> characters.
    */
   private void writeEscaped (String value) throws IOException {
     int nextQuoteChar = quoteCharacter.find(value, 0);

src/plugin/protocol-okhttp/src/java/org/apache/nutch/protocol/okhttp/OkHttp.java

@@ -236,34 +236,34 @@ public okhttp3.Response intercept(Interceptor.Chain chain)
       String httpProtocol = response.protocol().toString()
           .toUpperCase(Locale.ROOT);
       if (useHttp2 && "H2".equals(httpProtocol)) {
-        // back-warc compatible protocol name
+        // back-ward compatible protocol name
         httpProtocol = "HTTP/2";
       }
 
-      StringBuilder resquestverbatim = null;
+      StringBuilder requestverbatim = null;
       StringBuilder responseverbatim = null;
 
       if (storeHttpRequest) {
-        resquestverbatim = new StringBuilder();
+        requestverbatim = new StringBuilder();
 
-        resquestverbatim.append(request.method()).append(' ');
-        resquestverbatim.append(request.url().encodedPath());
+        requestverbatim.append(request.method()).append(' ');
+        requestverbatim.append(request.url().encodedPath());
         String query = request.url().encodedQuery();
         if (query != null) {
-          resquestverbatim.append('?').append(query);
+          requestverbatim.append('?').append(query);
         }
-        resquestverbatim.append(' ').append(httpProtocol).append("\r\n");
+        requestverbatim.append(' ').append(httpProtocol).append("\r\n");
 
         Headers headers = request.headers();
 
         for (int i = 0, size = headers.size(); i < size; i++) {
           String key = headers.name(i);
           String value = headers.value(i);
-          resquestverbatim.append(key).append(": ").append(value)
+          requestverbatim.append(key).append(": ").append(value)
               .append("\r\n");
         }
 
-        resquestverbatim.append("\r\n");
+        requestverbatim.append("\r\n");
       }
 
       if (storeHttpHeaders) {
@@ -294,9 +294,9 @@ public okhttp3.Response intercept(Interceptor.Chain chain)
         builder = builder.header(Response.IP_ADDRESS, ipAddress);
       }
 
-      if (resquestverbatim != null) {
+      if (requestverbatim != null) {
         byte[] encodedBytesRequest = Base64.getEncoder()
-            .encode(resquestverbatim.toString().getBytes());
+            .encode(requestverbatim.toString().getBytes());
         builder = builder.header(Response.REQUEST,
             new String(encodedBytesRequest));
       }

src/plugin/scoring-orphan/src/test/org/apache/nutch/scoring/orphan/TestOrphanScoringFilter.java

@@ -91,7 +91,7 @@ public void testOrphanScoringFilter() throws Exception {
             + CrawlDatum.getStatusName(datum.getStatus()),
         CrawlDatum.STATUS_DB_NOTMODIFIED, datum.getStatus());
 
-    // Wait until mark.gone.after
+    // Wait until scoring.orphan.mark.gone.after
     try {
       Thread.sleep(5000);
     } catch (Exception e) {
@@ -106,7 +106,7 @@ public void testOrphanScoringFilter() throws Exception {
             + CrawlDatum.getStatusName(datum.getStatus()),
         CrawlDatum.STATUS_DB_GONE, datum.getStatus());
 
-    // Wait until mark.orphan.after
+    // Wait until scoring.orphan.mark.orphan.after
     try {
       Thread.sleep(5000);
     } catch (Exception e) {

src/test/org/apache/nutch/crawl/TestGenerator.java

@@ -131,7 +131,7 @@ public int compare(URLCrawlDatum tuple1, URLCrawlDatum tuple2) {
   }
 
   /**
-   * Test that generator obeys the property "generate.max.per.host".
+   * Test that generator obeys the property "generate.max.count".
    * 
    * @throws Exception
    */
@@ -195,8 +195,8 @@ public void testGenerateHostLimit() throws Exception {
   }
 
   /**
-   * Test that generator obeys the property "generator.max.count" and
-   * "generator.count.per.domain".
+   * Test that generator obeys the property "generate.max.count" and
+   * "generate.count.mode".
    * 
    * @throws Exception
    */