|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object org.archive.crawler.io.CrawlerJournal
public class CrawlerJournal
Utility class for a crawler journal/log that is compressed and rotates by serial number at checkpoints.
Field Summary | |
---|---|
protected it.unimi.dsi.mg4j.util.MutableString |
accumulatingBuffer
Allocate a buffer for accumulating lines to write and reuse it. |
static java.lang.String |
GZIP_SUFFIX
suffix to recognize gzipped files |
protected java.io.File |
gzipFile
File we're writing journal to. |
protected long |
lines
line count |
static java.lang.String |
LOG_ERROR
prefix for error lines |
static java.lang.String |
LOG_TIMESTAMP
prefix for timestamp lines |
protected java.io.Writer |
out
Stream on which we record frontier events. |
protected int |
timestamp_interval
number of lines between timestamps |
Constructor Summary | |
---|---|
CrawlerJournal(java.io.File file)
Create a new crawler journal at the given location |
|
CrawlerJournal(java.lang.String path,
java.lang.String filename)
Create a new crawler journal at the given location |
Method Summary | |
---|---|
void |
checkpoint(java.io.File checkpointDir)
Handle a checkpoint by rotating the current log to a checkpoint-named file and starting a new log. |
void |
close()
Flush and close the underlying IO objects. |
protected void |
considerTimestamp()
Write a timestamp line if appropriate |
static java.io.BufferedInputStream |
getBufferedInput(java.io.File source)
Get a BufferedInputStream on the recovery file given. |
static java.io.BufferedReader |
getBufferedReader(java.io.File source)
Get a BufferedReader on the crawler journal given |
static java.io.BufferedReader |
getBufferedReader(java.net.URL source)
Get a BufferedReader on the crawler journal given. |
protected java.io.Writer |
initialize(java.io.File f)
|
protected void |
noteLine()
Count and note a line |
void |
seriousError(java.lang.String err)
Note a serious error vioa a special log line |
void |
writeLine(it.unimi.dsi.mg4j.util.MutableString mstring)
Write a line. |
void |
writeLine(java.lang.String string)
Write a line |
void |
writeLine(java.lang.String s1,
java.lang.String s2)
Write a line of two strings |
void |
writeLine(java.lang.String s1,
java.lang.String s2,
java.lang.String s3)
Write a line of three strings |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final java.lang.String LOG_ERROR
public static final java.lang.String LOG_TIMESTAMP
protected java.io.Writer out
protected long lines
protected int timestamp_interval
public static final java.lang.String GZIP_SUFFIX
protected java.io.File gzipFile
protected it.unimi.dsi.mg4j.util.MutableString accumulatingBuffer
Constructor Detail |
---|
public CrawlerJournal(java.lang.String path, java.lang.String filename) throws java.io.IOException
path
- Directory to make thejournal in.filename
- Name to use for journal file.
java.io.IOException
public CrawlerJournal(java.io.File file) throws java.io.IOException
file
- path at which to make journal
java.io.IOException
Method Detail |
---|
public static java.io.BufferedReader getBufferedReader(java.io.File source) throws java.io.IOException
source
- File journal
java.io.IOException
public static java.io.BufferedReader getBufferedReader(java.net.URL source) throws java.io.IOException
source
- URL journal
java.io.IOException
public static java.io.BufferedInputStream getBufferedInput(java.io.File source) throws java.io.IOException
source
- file to open
java.io.IOException
protected java.io.Writer initialize(java.io.File f) throws java.io.FileNotFoundException, java.io.IOException
java.io.FileNotFoundException
java.io.IOException
public void writeLine(java.lang.String string)
string
- Stringpublic void writeLine(java.lang.String s1, java.lang.String s2)
s1
- Strings2
- Stringpublic void writeLine(java.lang.String s1, java.lang.String s2, java.lang.String s3)
s1
- Strings2
- Strings3
- Stringpublic void writeLine(it.unimi.dsi.mg4j.util.MutableString mstring)
mstring
- MutableString to writeprotected void noteLine() throws java.io.IOException
java.io.IOException
protected void considerTimestamp() throws java.io.IOException
java.io.IOException
public void close()
public void seriousError(java.lang.String err)
err
- public void checkpoint(java.io.File checkpointDir) throws java.io.IOException
checkpointDir
-
java.io.IOException
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |