Nutch2.2.3源码阅读之injectorJob

injectorJob是Nutch中第一个模块。它的功能是对URL进行优先值排序并存到本地列表中。

nutch中URL是按行存储的，每行的结构如下： http://www.nutch.org/ \t nutch.score=10 \t nutch.fetchInterval=2592000 * \t userType=open_source

程序的入口如下：

  int res = ToolRunner.run(NutchConfiguration.create(), new InjectorJob(),args);

其中NutchCofiguration是一个配置nutch的类，在这不详述。主要是看injectorJob方法。在InjectorJob类中，定义了一个UrlMapper用来继承Mapper类并实现map函数，在这里面没有reduce函数。

 @Override    protected void setup(Context context) throws IOException, InterruptedException {      urlNormalizers = new URLNormalizers(context.getConfiguration(),      URLNormalizers.SCOPE_INJECT);      interval = context.getConfiguration().getInt("db.fetch.interval.default",2592000);      filters = new URLFilters(context.getConfiguration());      scfilters = new ScoringFilters(context.getConfiguration());      scoreInjected = context.getConfiguration().getFloat("db.score.injected",          1.0f);      curTime = context.getConfiguration().getLong("injector.current.time",          System.currentTimeMillis());    }

这是Mapper类中的setup函数，在此过程中进行了参数定义。分别是归一化方法（urlNormalizers）,间隔（interval？？？），两个过滤器(URLFilters、ScoringFilters),以及当前时间和分数写入。

protected void map(LongWritable key, Text value, Context context)        throws IOException, InterruptedException {      String url = value.toString().trim(); // value is line of text      if (url != null && (url.length() == 0 || url.startsWith("#"))) {        /* Ignore line that start with # */        return;      }      // if tabs : metadata that could be stored      // must be name=value and separated by \t      float customScore = -1f;      int customInterval = interval;      Map<String, String> metadata = new TreeMap<String, String>();      if (url.indexOf("\t") != -1) {        String[] splits = url.split("\t");        url = splits[0];        for (int s = 1; s < splits.length; s++) {          // find separation between name and value          int indexEquals = splits[s].indexOf("=");          if (indexEquals == -1) {            // skip anything without a =            continue;          }          String metaname = splits[s].substring(0, indexEquals);          String metavalue = splits[s].substring(indexEquals + 1);          if (metaname.equals(nutchScoreMDName)) {            try {              customScore = Float.parseFloat(metavalue);            } catch (NumberFormatException nfe) {            }          } else if (metaname.equals(nutchFetchIntervalMDName)) {            try {              customInterval = Integer.parseInt(metavalue);            } catch (NumberFormatException nfe) {            }          } else            metadata.put(metaname, metavalue);        }      }      try {        url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);        url = filters.filter(url); // filter the url      } catch (Exception e) {        LOG.warn("Skipping " + url + ":" + e);        url = null;      }      if (url == null) {        context.getCounter("injector", "urls_filtered").increment(1);        return;      } else { // if it passes        String reversedUrl = TableUtil.reverseUrl(url); // collect it        WebPage row = WebPage.newBuilder().build();        row.setFetchTime(curTime);        row.setFetchInterval(customInterval);        // now add the metadata        Iterator<String> keysIter = metadata.keySet().iterator();        while (keysIter.hasNext()) {          String keymd = keysIter.next();          String valuemd = metadata.get(keymd);          row.getMetadata().put(new Utf8(keymd),              ByteBuffer.wrap(valuemd.getBytes()));        }        if (customScore != -1)          row.setScore(customScore);        else          row.setScore(scoreInjected);        try {          scfilters.injectedScore(url, row);        } catch (ScoringFilterException e) {          if (LOG.isWarnEnabled()) {            LOG.warn("Cannot filter injected score for url " + url                + ", using default (" + e.getMessage() + ")");          }        }        context.getCounter("injector", "urls_injected").increment(1);        row.getMarkers()            .put(DbUpdaterJob.DISTANCE, new Utf8(String.valueOf(0)));        Mark.INJECT_MARK.putMark(row, YES_STRING);        context.write(reversedUrl, row);      }    }  }

这是主要的map函数,在这个函数中做了以下事情。
1.是对每个读入的URL进行格式处理，包括取出两边的空格

String url = value.toString().trim();

忽略开头的’#’

if (url != null && (url.length() == 0 || url.startsWith("#"))) {        /* Ignore line that start with # */        return;      }

已知URL的格式

 http://www.nutch.org/ \t nutch.score=10 \t nutch.fetchInterval=2592000 * \t userType=open_source

对其进行如下处理

  Map<String, String> metadata = new TreeMap<String, String>();      if (url.indexOf("\t") != -1) {        String[] splits = url.split("\t");        url = splits[0];        for (int s = 1; s < splits.length; s++) {          // find separation between name and value          int indexEquals = splits[s].indexOf("=");          if (indexEquals == -1) {            // skip anything without a =            continue;          }          String metaname = splits[s].substring(0, indexEquals);          String metavalue = splits[s].substring(indexEquals + 1);          if (metaname.equals(nutchScoreMDName)) {            try {              customScore = Float.parseFloat(metavalue);            } catch (NumberFormatException nfe) {            }          } else if (metaname.equals(nutchFetchIntervalMDName)) {            try {              customInterval = Integer.parseInt(metavalue);            } catch (NumberFormatException nfe) {            }          } else            metadata.put(metaname, metavalue);        }      }

首先将其按照’\t’分片，第一个显然是url,然后根据’=’解析出name和value值。

try {        url = urlNormalizers.normalize(url, URLNormalizers.SCOPE_INJECT);        url = filters.filter(url); // filter the url      } catch (Exception e) {        LOG.warn("Skipping " + url + ":" + e);        url = null;      }      if (url == null) {        context.getCounter("injector", "urls_filtered").increment(1);        return;      } else { // if it passes        String reversedUrl = TableUtil.reverseUrl(url); // collect it        WebPage row = WebPage.newBuilder().build();        row.setFetchTime(curTime);        row.setFetchInterval(customInterval);        // now add the metadata        Iterator<String> keysIter = metadata.keySet().iterator();        while (keysIter.hasNext()) {          String keymd = keysIter.next();          String valuemd = metadata.get(keymd);          row.getMetadata().put(new Utf8(keymd),              ByteBuffer.wrap(valuemd.getBytes()));        }        if (customScore != -1)          row.setScore(customScore);        else          row.setScore(scoreInjected);        try {          scfilters.injectedScore(url, row);        } catch (ScoringFilterException e) {          if (LOG.isWarnEnabled()) {            LOG.warn("Cannot filter injected score for url " + url                + ", using default (" + e.getMessage() + ")");          }        }        context.getCounter("injector", "urls_injected").increment(1);        row.getMarkers()            .put(DbUpdaterJob.DISTANCE, new Utf8(String.valueOf(0)));        Mark.INJECT_MARK.putMark(row, YES_STRING);        context.write(reversedUrl, row);      }

对URL进行归一化以及过滤,若URL为空，则context计数器加一，否则进行如下处理。
首先翻转URL

String org.apache.nutch.util.TableUtil.reverseUrl(String urlString) throws MalformedURLExceptionReverses a url's domain. This form is better for storing in hbase. Because scans within the same domain are faster.E.g. "http://bar.foo.com:8983/to/index.html?a=b" becomes "com.foo.bar:8983:http/to/index.html?a=b".

这里用到reverseURL,API写的很清楚。

 Iterator<String> keysIter = metadata.keySet().iterator();        while (keysIter.hasNext()) {          String keymd = keysIter.next();          String valuemd = metadata.get(keymd);          row.getMetadata().put(new Utf8(keymd),              ByteBuffer.wrap(valuemd.getBytes()));        }

在这里遍历metadata树图，对每个key值写入相应的value。
之后是对其写入Filter score，最后写入context中的是翻转后的URL机webpage类的row。
之后是负责创建Job的run()函数

public Map<String, Object> run(Map<String, Object> args) throws Exception {    getConf().setLong("injector.current.time", System.currentTimeMillis());    Path input;    Object path = args.get(Nutch.ARG_SEEDDIR);    if (path instanceof Path) {      input = (Path) path;    } else {      input = new Path(path.toString());    }    numJobs = 1;    currentJobNum = 0;    currentJob = NutchJob.getInstance(getConf(), "inject " + input);    FileInputFormat.addInputPath(currentJob, input);    currentJob.setMapperClass(UrlMapper.class);    currentJob.setMapOutputKeyClass(String.class);    currentJob.setMapOutputValueClass(WebPage.class);    currentJob.setOutputFormatClass(GoraOutputFormat.class);    DataStore<String, WebPage> store = StorageUtils.createWebStore(        currentJob.getConfiguration(), String.class, WebPage.class);    GoraOutputFormat.setOutput(currentJob, store, true);    // NUTCH-1471 Make explicit which datastore class we use    Class<? extends DataStore<Object, Persistent>> dataStoreClass = StorageUtils        .getDataStoreClass(currentJob.getConfiguration());    LOG.info("InjectorJob: Using " + dataStoreClass        + " as the Gora storage class.");    currentJob.setReducerClass(Reducer.class);    currentJob.setNumReduceTasks(0);    currentJob.waitForCompletion(true);    ToolUtil.recordJobStatus(null, currentJob, results);    // NUTCH-1370 Make explicit #URLs injected @runtime    long urlsInjected = currentJob.getCounters()        .findCounter("injector", "urls_injected").getValue();    long urlsFiltered = currentJob.getCounters()        .findCounter("injector", "urls_filtered").getValue();    LOG.info("InjectorJob: total number of urls rejected by filters: "        + urlsFiltered);    LOG.info("InjectorJob: total number of urls injected after normalization and filtering: "        + urlsInjected);    return results;  }

首先是对输入路径进行处理，然后是创建Map Job，
currentJob是实例化的一个Nutch Job，对currentJob进行map/reduce设置。

  currentJob.setMapperClass(UrlMapper.class);    currentJob.setMapOutputKeyClass(String.class);    currentJob.setMapOutputValueClass(WebPage.class);    currentJob.setOutputFormatClass(GoraOutputFormat.class);

GoraOutPutFormat是apache的一个项目，定义了一种输出格式。

  DataStore<String, WebPage> store = StorageUtils.createWebStore(        currentJob.getConfiguration(), String.class, WebPage.class);    GoraOutputFormat.setOutput(currentJob, store, true);

建立一个Gora形式的储存样例，之后将输出形式设置为当前的job，以及储存地点。

 currentJob.setReducerClass(Reducer.class);    currentJob.setNumReduceTasks(0);    currentJob.waitForCompletion(true);    ToolUtil.recordJobStatus(null, currentJob, results);

设置无educe过程，及向系统记录job状态

之后一个run函数负责开始一段injector job，在此不说。