revise readme

Author: a13519

README.md

@@ -14,12 +14,27 @@ A handy tool named **Bold/CompressedComparator** can compare two tables to figur
 
 ## Concept 
 
+### Headers
+When the data is parsed, the first row (after ignored rows before it) is treated as headers. And the columns referenced by this header. 
+
+### Compressed 
+The Data carried by Table can be compressed to reduce the size of execution profile. Also it can be disabled by setting 
+```java
+CompressedTableFactory
+        .build("csv")
+        .compressed(false)
+        .build();
+```
+This is useful in handling large data set.
+
 ### Table Type
 * CSV: the source type of CSV file to parse
 * Excel: the source type of Excel file to parse
 
-### Keys
+### Key Sets
 When a Table is parsed, the key set need to be set to Table thus table knows how to index the content and later those data can be queried. Each KeySet contains one or multiple columns which are represended by headers. 
+To understand multiple Key Sets, you can imagine the name card, one person(Row in the case) could have multiple name cards, one is business card the other may be a social name card or family card, the name or identification on the card could be different but the purpose is to reveal to link it to the real human identity.
+Here, in Table, a Row could have multiple Keys to represent itself.
 
 One **Bold/KeySet** contains:
 * One or Multiple headers or Columns
@@ -34,11 +49,24 @@ The **Bold/KeyHeadersList** represents the KeySets.
 ### Delimeter
 This is for CSV parsing, a delimeter can be specified if it is other than comma
 
+## Comparison
+The Compressed Comparator is to compare two Tables to find out the disparities.
+
+### ComparatorListener
+This is a call back interface usd by comparator to let outside world known what's happened during the process.
 
+### CompressedComparatorFactory
+This is the factory to initialize the Comparator you prefer. 
+* before() and after() to specify two tables
+* ignoredFields() to set the Fields/Columns you don't want to compare thus fields won't appear in result
+* comparatorListener() to set the call back listener
+* trim() is to let the process trim the data fields or not
+* strictMissed() this is the switch in case the columns are missed in before or after, and it is to enable the comparison on this column. If it is true, then any rows in the tables will be mismatch if there are any missed columns in table.
 
 ## Examples
 
-### Parse a table
+### Parse a table with single key set
+In this case, the key is composition keys of two columns of "Customer Id" and "First Name":
 ```java
 CompressedTable beforetable = CompressedTableFactory
         .build("csv")
@@ -53,3 +81,32 @@ CompressedTable beforetable = CompressedTableFactory
                 .toAbsolutePath()
                 .toString());
 ```
+
+### Parse a table with multiple key sets
+In this case, there are two key sets used to identify a row by one set of {"Customer Id", "First Name"}, the other key set is {"Phone 1", "Phone 2", "Email"}
+```java
+CompressedTable beforetable = CompressedTableFactory
+        .build("csv")
+        .keyHeaderList(new KeyHeadersList()
+                    .addHeaders(new String[]{"First Name", "Last Name"})
+                    .addHeaders(new String[]{"Phone 1", "Phone 2", "Email"})
+                )
+                .ignoredLines(0)
+                .delimeter(',')
+                .parse(Paths.get("customers-1000b.csv")
+                        .toAbsolutePath()
+                        .toString());
+```
+
+### Compare two tables
+
+```java
+        CompressedComparatorFactory.builder()
+                .before(beforetable)
+                .after(aftertable)
+                .comparatorListener(listener)
+                .strictMissed(false)
+                .ignoredFields(new HashSet(Arrays.asList(new String[]{})))
+                .build().create()
+                .compare();
+```

src/main/java/samples/CompareTwoTables.java

@@ -0,0 +1,65 @@
+package samples;
+
+import lombok.extern.log4j.Log4j2;
+import net.zousys.compressedtable.CompressedComparatorFactory;
+import net.zousys.compressedtable.CompressedTableFactory;
+import net.zousys.compressedtable.impl.CompressedTable;
+import net.zousys.compressedtable.impl.KeyHeadersList;
+
+import java.io.IOException;
+import java.nio.file.Paths;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.zip.DataFormatException;
+
+@Log4j2
+public class CompareTwoTables {
+    /**
+     *
+     * @param args
+     * @throws IOException
+     * @throws DataFormatException
+     */
+    public static void main(String[] args) throws IOException, DataFormatException {
+        CompareListener listener = new CompareListener();
+
+        CompressedTable beforetable = CompressedTableFactory
+                .build("csv")
+                .keyHeaderList(new KeyHeadersList()
+                        .addHeaders(new String[]{"Customer Id", "First Name"})
+                )
+                .compressed(true)
+                .ignoredLines(0)
+                .delimeter(',')
+                .parse(Paths.get("customers-1000b.csv")
+                        .toAbsolutePath()
+                        .toString());
+        listener.handleBeforeLoaded(beforetable);
+        log.info("Before size: " + beforetable.getContents().size() + " " + beforetable.getHeaders() + " Mode: " + beforetable.getMode());
+
+        CompressedTable aftertable = CompressedTableFactory
+                .build("csv")
+                .keyHeaderList(new KeyHeadersList()
+                        .addHeaders(new String[]{"Customer Id", "First Name"})
+                )
+                .compressed(true)
+                .ignoredLines(0)
+                .delimeter(',')
+                .parse(Paths.get("customers-1000a.csv")
+                        .toAbsolutePath()
+                        .toString());
+        listener.handleAfterLoaded(aftertable);
+        log.info("After size: " + aftertable.getContents().size() + " " + aftertable.getHeaders() + " Mode: " + beforetable.getMode());
+
+        CompressedComparatorFactory.builder()
+                .before(beforetable)
+                .after(aftertable)
+                .comparatorListener(listener)
+                .ignoredFields(new HashSet(Arrays.asList(new String[]{})))
+                .strictMissed(true)
+                .build().create()
+                .compare();
+
+    }
+
+}

src/main/java/samples/Main.java

@@ -0,0 +1,42 @@
+package samples;
+
+import lombok.extern.log4j.Log4j2;
+import net.zousys.compressedtable.CompressedComparatorFactory;
+import net.zousys.compressedtable.CompressedTableFactory;
+import net.zousys.compressedtable.impl.CompressedTable;
+import net.zousys.compressedtable.impl.KeyHeadersList;
+
+import java.io.IOException;
+import java.nio.file.Paths;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.zip.DataFormatException;
+
+@Log4j2
+public class ParseMultipleKeySets {
+    /**
+     * Default the Table is compressed. This is to parse a CSV file to compressed table.
+     *
+     * @param args
+     * @throws IOException
+     * @throws DataFormatException
+     */
+    public static void main(String[] args) throws IOException, DataFormatException {
+        CompareListener k = new CompareListener();
+
+        CompressedTable beforetable = CompressedTableFactory
+                .build("csv")
+                .keyHeaderList(new KeyHeadersList()
+                        .addHeaders(new String[]{"First Name", "Last Name"})
+                        .addHeaders(new String[]{"Phone 1", "Phone 2", "Email"})
+                )
+                .ignoredLines(0)
+                .delimeter(',')
+                .parse(Paths.get("customers-1000b.csv")
+                        .toAbsolutePath()
+                        .toString());
+        k.handleBeforeLoaded(beforetable);
+        log.info("Before size: " + beforetable.getContents().size() + " " + beforetable.getHeaders());
+    }
+
+}

src/main/java/samples/ParseMultipleKeySets.java

@@ -0,0 +1,41 @@
+package samples;
+
+import lombok.extern.log4j.Log4j2;
+import net.zousys.compressedtable.CompressedComparatorFactory;
+import net.zousys.compressedtable.CompressedTableFactory;
+import net.zousys.compressedtable.impl.CompressedTable;
+import net.zousys.compressedtable.impl.KeyHeadersList;
+
+import java.io.IOException;
+import java.nio.file.Paths;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.zip.DataFormatException;
+
+@Log4j2
+public class ParseSingleKeySet {
+    /**
+     * This is to parse a Single Key Set CSV file to an un-compressed table
+     * @param args
+     * @throws IOException
+     * @throws DataFormatException
+     */
+    public static void main(String[] args) throws IOException, DataFormatException {
+        CompareListener listener = new CompareListener();
+
+        CompressedTable beforetable = CompressedTableFactory
+                .build("csv")
+                .keyHeaderList(new KeyHeadersList()
+                        .addHeaders(new String[]{"Customer Id", "First Name"})
+                )
+                .compressed(false)
+                .ignoredLines(0)
+                .delimeter(',')
+                .parse(Paths.get("customers-1000b.csv")
+                        .toAbsolutePath()
+                        .toString());
+        listener.handleBeforeLoaded(beforetable);
+        log.info("Before size: " + beforetable.getContents().size() + " " + beforetable.getHeaders() + " Mode: " + beforetable.getMode());
+
+    }
+}