Add table graph tutorial

RomualdRousseau · Apr 30, 2024 · 6b3ba74 · 6b3ba74
1 parent a6ccd05
commit 6b3ba74
Show file tree

Hide file tree

Showing 14 changed files with 117 additions and 282 deletions.
diff --git a/data/AG120-N-074.pdf b/data/AG120-N-074.pdf
diff --git a/dependencies b/dependencies
@@ -33,12 +33,12 @@ com.github.romualdrousseau:shuju-jackson:jar:1.23
 com.fasterxml.jackson.core:jackson-databind:jar:2.15.2
 com.fasterxml.jackson.core:jackson-annotations:jar:2.15.2
 com.fasterxml.jackson.core:jackson-core:jar:2.15.2
-com.github.romualdrousseau:any2json:jar:20240422.102355-9:2.38-SNAPSHOT
+com.github.romualdrousseau:any2json:jar:2.38
 org.python:jython-standalone:jar:2.7.3
-com.github.romualdrousseau:any2json-layex-parser:jar:20240314.021346-4:2.38-SNAPSHOT
-com.github.romualdrousseau:any2json-net-classifier:jar:20240314.021330-4:2.38-SNAPSHOT
-com.github.romualdrousseau:any2json-csv:jar:20240314.021455-2:2.38-SNAPSHOT
-com.github.romualdrousseau:any2json-excel:jar:20240314.021620-3:2.38-SNAPSHOT
+com.github.romualdrousseau:any2json-layex-parser:jar:2.38
+com.github.romualdrousseau:any2json-net-classifier:jar:2.38
+com.github.romualdrousseau:any2json-csv:jar:2.38
+com.github.romualdrousseau:any2json-excel:jar:2.38
 org.apache.poi:poi:jar:5.2.3
 commons-codec:commons-codec:jar:1.15
 org.apache.commons:commons-collections4:jar:4.4
@@ -51,7 +51,7 @@ org.apache.xmlbeans:xmlbeans:jar:5.1.1
 org.apache.commons:commons-compress:jar:1.21
 com.github.virtuald:curvesapi:jar:1.07
 org.apache.poi:poi-scratchpad:jar:5.2.3
-com.github.romualdrousseau:any2json-pdf:jar:20240419.045004-6:2.38-SNAPSHOT
+com.github.romualdrousseau:any2json-pdf:jar:2.38
 technology.tabula:tabula:jar:1.0.5
 org.locationtech.jts:jts-core:jar:1.18.1
 org.slf4j:slf4j-simple:jar:1.7.32

diff --git a/docs/how_it_works.md b/docs/how_it_works.md
diff --git a/docs/index.md b/docs/index.md
@@ -1,4 +1,4 @@
-# Welcome to Any2Json Documents
+# Welcome to PyAny2Json Documents
 
 ***Revolutionizing Data Management: The Transformative Potential of a Novel Framework for Semi-Structured Documents***
 
@@ -11,26 +11,10 @@
 * [Tutorial 5 - Data extraction with pivot](tutorial_5.md)
 * [Tutorial 6 - More complex noise reduction](tutorial_6.md)
 * [Tutorial 7 - Data extraction from PDF](tutorial_7.md)
-* [Tutorial 8 - Make a classifier from scratch](tutorial_8.md)
+* [Tutorial 8 - Data extraction from paginated PDF](tutorial_8.md)
+* [Tutorial 9 - Browse the table grah](tutorial_9.md)
+* [Tutorial 10 - Make a classifier from scratch](tutorial_10.md)
 
 ## How it works
 
-* Please find detailed explanations on how Any2json works and its unique features [here](how_it_works.md)
-
-## Plugins
-
-* [Any2Json Layex Parser](https://github.com/RomualdRousseau/Any2Json-Layex-Parser/)
-* [Any2Json Net Classifier](https://github.com/RomualdRousseau/Any2Json-Net-Classifier/)
-* [Any2Json Csv](https://github.com/RomualdRousseau/Any2Json-Csv/)
-* [Any2Json Excel](https://github.com/RomualdRousseau/Any2Json-Excel/)
-* [Any2Json Dbf](https://github.com/RomualdRousseau/Any2Json-Dbf/)
-* [Any2Json Parquet](https://github.com/RomualdRousseau/Any2Json-Parquet/)
-* [Any2Json Pdf](https://github.com/RomualdRousseau/Any2Json-Pdf/)
-
-## Models
-
-* [Models](https://github.com/RomualdRousseau/Any2Json-Models/)
-
-## Resources
-
-* [White Papers](white_papers.md)
+* Please find detailed explanations on how Any2json works and its unique features [here](https://romualdrousseau.github.io/Any2Json-Documents/)
diff --git a/docs/objects.txt b/docs/objects.txt
diff --git a/docs/patents.md b/docs/patents.md
diff --git a/docs/tutorial_10.md b/docs/tutorial_10.md
@@ -0,0 +1,13 @@
+# Tutorial 10 - Make a classifier from scratch
+
+[View source on GitHub](https://github.com/RomualdRousseau/Any2Json-Examples).
+
+This tutoral is a continuation of the [Tutorial 9](tutorial_9.md).
+
+***Coming soon***
+
+## Conclusion
+
+Congratulations! You have loaded documents using Any2Json.
+
+For more examples of using Any2Json, check out the [tutorials](index.md).
diff --git a/docs/tutorial_8.md b/docs/tutorial_8.md
@@ -1,4 +1,4 @@
-# Tutorial 8 - Make a classifier from scratch
+# Tutorial 8 - Data extraction from paginated PDF
 
 [View source on GitHub](https://github.com/RomualdRousseau/Any2Json-Examples).
 

diff --git a/docs/tutorial_9.md b/docs/tutorial_9.md
@@ -0,0 +1,13 @@
+# Tutorial 9 - Browse the table grah
+
+[View source on GitHub](https://github.com/RomualdRousseau/Any2Json-Examples).
+
+This tutoral is a continuation of the [Tutorial 8](tutorial_8.md).
+
+***Coming soon***
+
+## Conclusion
+
+Congratulations! You have loaded documents using Any2Json.
+
+For more examples of using Any2Json, check out the [tutorials](index.md).
diff --git a/docs/white_papers.md b/docs/white_papers.md
diff --git a/examples/tutorial9.py b/examples/tutorial9.py
@@ -0,0 +1,40 @@
+from pyany2json import ModelBuilder, LayexTableParser, DocumentFactory, INTELLI_LAYOUT
+from pyany2json.document_factory import DataTable, TableGraph
+
+
+REPO_BASE_URL = "https://raw.githubusercontent.com/RomualdRousseau/Any2Json-Models/main"
+MODEL_NAME = "sales-english"
+FILE_PATH = "data/AG120-N-074.pdf"
+FILE_ENCODING = "UTF-8"
+
+
+builder = ModelBuilder().fromURI("{0}/{1}/{1}.json".format(REPO_BASE_URL, MODEL_NAME))
+parser = LayexTableParser(
+    [""], ["((vv$)(v+$v+$))(()(.+$)())+()", "(()(.+$))(()(.+$)())+()"]
+)
+model = (
+    builder.setTableParser(parser)
+    .build()
+)
+
+def visitTable(parent: TableGraph):
+    for c in parent.children():
+        table = c.getTable()
+        if isinstance(table, DataTable):
+            for header in table.headers():
+                print(header.getName(), end=" ")
+            print()
+            for row in table.rows():
+                for cell in row.cells():
+                    print(cell.getValue(), end=" ")
+                print()
+        if len(c.children()) > 0:
+            visitTable(c)
+
+with DocumentFactory.createInstance(FILE_PATH, FILE_ENCODING) as doc:
+    doc.setModel(model)
+    doc.setHints([INTELLI_LAYOUT])
+    for sheet in doc.sheets():
+        root = sheet.getTableGraph()
+        if root.isPresent():
+            visitTable(root.get())
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -1,5 +1,4 @@
-site_name: Any2Json Documents
+site_name: PyAny2Json Documents
 nav:
   - Home: index.md
-  - How it works: how_it_works.md
-  - White Papers: white_papers.md
+