Bug fix/fix tutorials (#24)

* fix: Fix and refactor tutorials * chore: Add icons * fix: Fix split tables replacing recursivity by a queue --------- Co-authored-by: Romuald Rousseau <[email protected]>
RomualdRousseau · Oct 17, 2024 · 069b877 · 069b877
1 parent 6eb68a6
commit 069b877
Show file tree

Hide file tree

Showing 18 changed files with 270 additions and 149 deletions.
diff --git a/archery-documents/icons/archery-open-graph.png b/archery-documents/icons/archery-open-graph.png
diff --git a/archery-examples/pom.xml b/archery-examples/pom.xml
@@ -51,6 +51,12 @@
             <artifactId>archery-pdf</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <!-- Log4j Framework -->
+        <dependency>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-slf4j2-impl</artifactId>
+            <version>${log4j.version}</version>
+        </dependency>
     </dependencies>
 
     <build>

diff --git a/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Common.java b/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Common.java
@@ -19,7 +19,7 @@
 
 public class Common {
     private static final Logger LOGGER = LoggerFactory.getLogger(Common.class);
-    private static final String REPO_BASE_URL = "https://raw.githubusercontent.com/RomualdRousseau/Archery/Archery-Models/main";
+    private static final String REPO_BASE_URL = "https://raw.githubusercontent.com/romualdrousseau/archery/main/archery-models";
 
     public static <T> JsonModelBuilder loadModelBuilder(final String modelName, final Class<T> clazz) {
         return new JsonModelBuilder().fromPath(Common.getResourcePath(String.format("/models/%s.json", modelName), clazz));

diff --git a/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial2.java b/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial2.java
@@ -1,29 +1,30 @@
 package com.github.romualdrousseau.archery.examples;
 
+import java.util.ArrayList;
 import java.util.EnumSet;
+import java.util.HashMap;
 import java.util.List;
+import java.util.Map;
 
 import com.github.romualdrousseau.archery.Document;
 import com.github.romualdrousseau.archery.DocumentFactory;
 import com.github.romualdrousseau.archery.parser.LayexTableParser;
 
 public class Tutorial2 implements Runnable {
 
-    public Tutorial2() {
+    public static void main(final String[] args) {
+        new Tutorial2().run();
     }
 
     @Override
     public void run() {
-        final var tableParser = new LayexTableParser(
-                List.of("(v.$)+"),
-                List.of("(()(S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
-
         final var builder = Common.loadModelBuilderFromGitHub("sales-english");
-        builder.setTableParser(tableParser);
-        builder.getEntityList().add("PRODUCTNAME");
-        builder.getPatternMap().put("\\D+\\dml", "PRODUCTNAME");
-        builder.getPatternMap().values().remove("PACKAGE");
-        final var model = builder.build();
+
+        final var model = builder
+                .setTableParser(this.customTableParser())
+                .setEntityList(this.customEntities(builder.getEntityList()))
+                .setPatternMap(this.customPatternMap(builder.getPatternMap()))
+                .build();
 
         final var file = Common.loadData("document with multiple tables.xlsx", this.getClass());
         try (final var doc = DocumentFactory.createInstance(file, "UTF-8")
@@ -37,7 +38,22 @@ public void run() {
         }
     }
 
-    public static void main(final String[] args) {
-        new Tutorial2().run();
+    private LayexTableParser customTableParser() {
+        return new LayexTableParser(
+                List.of("(v.$)+"),
+                List.of("(()(S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
+    }
+
+    private List<String> customEntities(final List<String> entities) {
+        final var result = new ArrayList<String>(entities);
+        result.add("PRODUCTNAME");
+        result.remove("PACKAGE");
+        return result;
+    }
+
+    private Map<String, String> customPatternMap(final Map<String, String> patterns) {
+        final var result = new HashMap<String, String>(patterns);
+        result.put("\\D+\\dml", "PRODUCTNAME");
+        return result;
     }
 }
diff --git a/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial3.java b/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial3.java
@@ -1,28 +1,30 @@
 package com.github.romualdrousseau.archery.examples;
 
+import java.util.ArrayList;
 import java.util.EnumSet;
+import java.util.HashMap;
 import java.util.List;
+import java.util.Map;
 
 import com.github.romualdrousseau.archery.Document;
 import com.github.romualdrousseau.archery.DocumentFactory;
 import com.github.romualdrousseau.archery.parser.LayexTableParser;
 
 public class Tutorial3 implements Runnable {
 
-    public Tutorial3() {
+    public static void main(final String[] args) {
+        new Tutorial3().run();
     }
 
     @Override
     public void run() {
-        final var tableParser = new LayexTableParser(
-                List.of("(v.$)+"),
-                List.of("(()(S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
-
         final var builder = Common.loadModelBuilderFromGitHub("sales-english");
-        builder.setTableParser(tableParser);
-        builder.getEntityList().add("PRODUCTNAME");
-        builder.getPatternMap().put("\\D+\\dml", "PRODUCTNAME");
-        final var model = builder.build();
+
+        final var model = builder
+                .setTableParser(this.customTableParser())
+                .setEntityList(this.customEntities(builder.getEntityList()))
+                .setPatternMap(this.customPatternMap(builder.getPatternMap()))
+                .build();
 
         final var file = Common.loadData("document with defect.xlsx", this.getClass());
         try (final var doc = DocumentFactory.createInstance(file, "UTF-8")
@@ -37,7 +39,22 @@ public void run() {
         }
     }
 
-    public static void main(final String[] args) {
-        new Tutorial3().run();
+    private LayexTableParser customTableParser() {
+        return new LayexTableParser(
+            List.of("(v.$)+"),
+            List.of("(()(S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
+    }
+
+    private List<String> customEntities(final List<String> entities) {
+        final var result = new ArrayList<String>(entities);
+        result.add("PRODUCTNAME");
+        result.remove("PACKAGE");
+        return result;
+    }
+
+    private Map<String, String> customPatternMap(final Map<String, String> patterns) {
+        final var result = new HashMap<String, String>(patterns);
+        result.put("\\D+\\dml", "PRODUCTNAME");
+        return result;
     }
 }
diff --git a/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial4.java b/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial4.java
@@ -1,43 +1,59 @@
 package com.github.romualdrousseau.archery.examples;
 
+import java.util.ArrayList;
 import java.util.EnumSet;
+import java.util.HashMap;
 import java.util.List;
+import java.util.Map;
 
 import com.github.romualdrousseau.archery.Document;
 import com.github.romualdrousseau.archery.DocumentFactory;
 import com.github.romualdrousseau.archery.parser.LayexTableParser;
 
 public class Tutorial4 implements Runnable {
 
-    public Tutorial4() {
+    public static void main(final String[] args) {
+        new Tutorial4().run();
     }
 
     @Override
     public void run() {
-        final var tableParser = new LayexTableParser(
-                List.of("(v.$)+"),
-                List.of("(()(S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
-
         final var builder = Common.loadModelBuilderFromGitHub("sales-english");
-        builder.setTableParser(tableParser);
-        builder.getEntityList().add("PRODUCTNAME");
-        builder.getPatternMap().put("\\D+\\dml", "PRODUCTNAME");
-        final var model = builder.build();
+
+        final var model = builder
+                .setTableParser(this.customTableParser())
+                .setEntityList(this.customEntities(builder.getEntityList()))
+                .setPatternMap(this.customPatternMap(builder.getPatternMap()))
+                .build();
 
         final var file = Common.loadData("document with multiple tables.xlsx", this.getClass());
         try (final var doc = DocumentFactory.createInstance(file, "UTF-8")
                 .setModel(model)
                 .setHints(EnumSet.of(Document.Hint.INTELLI_LAYOUT, Document.Hint.INTELLI_TAG))
                 .setRecipe("sheet.setCapillarityThreshold(0)")) {
-
             doc.sheets().forEach(s -> Common.addSheetDebugger(s).getTable().ifPresent(t -> {
                 Common.printTags(t.headers());
                 Common.printRows(t.rows());
             }));
         }
     }
 
-    public static void main(final String[] args) {
-        new Tutorial4().run();
+    private LayexTableParser customTableParser() {
+        return new LayexTableParser(
+                List.of("(v.$)+"),
+                List.of("(()(S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
+    }
+
+    private List<String> customEntities(final List<String> entities) {
+        final var result = new ArrayList<String>(entities);
+        result.add("PRODUCTNAME");
+        result.remove("PACKAGE");
+        return result;
+    }
+
+    private Map<String, String> customPatternMap(final Map<String, String> patterns) {
+        final var result = new HashMap<String, String>(patterns);
+        result.put("\\D+\\dml", "PRODUCTNAME");
+        return result;
     }
 }
diff --git a/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial5.java b/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial5.java
@@ -1,29 +1,30 @@
 package com.github.romualdrousseau.archery.examples;
 
+import java.util.ArrayList;
 import java.util.EnumSet;
+import java.util.HashMap;
 import java.util.List;
+import java.util.Map;
 
 import com.github.romualdrousseau.archery.Document;
 import com.github.romualdrousseau.archery.DocumentFactory;
 import com.github.romualdrousseau.archery.parser.LayexTableParser;
 
 public class Tutorial5 implements Runnable {
 
-    public Tutorial5() {
+    public static void main(final String[] args) {
+        new Tutorial5().run();
     }
 
     @Override
     public void run() {
-        final var tableParser = new LayexTableParser(
-                List.of("(v.$)+"),
-                List.of("(()(S+$S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
-
         final var builder = Common.loadModelBuilderFromGitHub("sales-english");
-        builder.setTableParser(tableParser);
-        builder.getEntityList().add("PRODUCTNAME");
-        builder.getPatternMap().put("\\D+\\dml", "PRODUCTNAME");
-        builder.getPatternMap().put("(?i)((20|19)\\d{2}-(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)-\\d{2})", "DATE");
-        final var model = builder.build();
+
+        final var model = builder
+                .setTableParser(this.customTableParser())
+                .setEntityList(this.customEntities(builder.getEntityList()))
+                .setPatternMap(this.customPatternMap(builder.getPatternMap()))
+                .build();
 
         final var file = Common.loadData("document with pivot.xlsx", this.getClass());
         try (final var doc = DocumentFactory.createInstance(file, "UTF-8")
@@ -33,15 +34,30 @@ public void run() {
                         "sheet.setCapillarityThreshold(0)",
                         "sheet.setPivotOption(\"WITH_TYPE_AND_VALUE\")",
                         "sheet.setPivotTypeFormat(\"%s\")")) {
-
             doc.sheets().forEach(s -> Common.addSheetDebugger(s).getTable().ifPresent(t -> {
                 Common.printTags(t.headers());
                 Common.printRows(t.rows());
             }));
         }
     }
 
-    public static void main(final String[] args) {
-        new Tutorial5().run();
+    private LayexTableParser customTableParser() {
+        return new LayexTableParser(
+                List.of("(v.$)+"),
+                List.of("(()(S+$S+$))(()([/^TOTAL/|v].+$)())+(/TOTAL/.+$)"));
+    }
+
+    private List<String> customEntities(final List<String> entities) {
+        final var result = new ArrayList<String>(entities);
+        result.add("PRODUCTNAME");
+        result.remove("PACKAGE");
+        return result;
+    }
+
+    private Map<String, String> customPatternMap(final Map<String, String> patterns) {
+        final var result = new HashMap<String, String>(patterns);
+        result.put("\\D+\\dml", "PRODUCTNAME");
+        result.put("(?i)((20|19)\\d{2}-(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)-\\d{2})", "DATE");
+        return result;
     }
 }
diff --git a/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial6.java b/archery-examples/src/main/java/com/github/romualdrousseau/archery/examples/Tutorial6.java
@@ -9,25 +9,24 @@
 
 public class Tutorial6 implements Runnable {
 
-    public Tutorial6() {
+    public static void main(final String[] args) {
+        new Tutorial6().run();
     }
 
     @Override
     public void run() {
-        final var tableParser = new LayexTableParser(
-                List.of("(v.$)+"),
-                List.of("(()(E+$E+$))(()(/^PRODUCTCODE/.+$)*(/PRODUCTCODE/.+$))+()"));
-
         final var builder = Common.loadModelBuilderFromGitHub("sales-english");
-        builder.setTableParser(tableParser);
-        final var model = builder.build();
+
+        final var model = builder
+                .setTableParser(this.customTableParser())
+                .build();
 
         final var file = Common.loadData("document with noises.xls", this.getClass());
         try (final var doc = DocumentFactory.createInstance(file, "UTF-8")
                 .setModel(model)
                 .setHints(EnumSet.of(Document.Hint.INTELLI_LAYOUT))
                 .setRecipe(
-                    "sheet.setCapillarityThreshold(1.5)",
+                        "sheet.setCapillarityThreshold(1.5)",
                         "sheet.setDataTableParserFactory(\"DataTableGroupSubFooterParserFactory\")",
                         "sheet.dropRowsWhenFillRatioLessThan(0.2)")) {
 
@@ -38,7 +37,9 @@ public void run() {
         }
     }
 
-    public static void main(final String[] args) {
-        new Tutorial6().run();
+    private LayexTableParser customTableParser() {
+        return new LayexTableParser(
+                List.of("(v.$)+"),
+                List.of("(()(E+$E+$))(()(/^PRODUCTCODE/.+$)*(/PRODUCTCODE/.+$))+()"));
     }
 }