Merge branch 'master' into dependabot/maven/org.locationtech.jts-jts-…

…core-1.19.0

.github/workflows/tests-windows.yml

@@ -1,4 +1,4 @@
-name: Java CI
+name: Java CI (Windows)
 
 on: [push]
 
@@ -7,9 +7,14 @@ jobs:
     runs-on: windows-latest
 
     steps:
-      - uses: actions/checkout@v2
+      # https://github.com/actions/checkout/issues/135#issuecomment-602171132
+      - name: Set git to use LF
+        run: |
+          git config --global core.autocrlf false
+          git config --global core.eol lf
+      - uses: actions/checkout@v3
       - name: Set up JDK 11
-        uses: actions/setup-java@v2
+        uses: actions/setup-java@v3
         with:
           java-version: '11'
           distribution: 'adopt'

.github/workflows/tests.yml

@@ -1,15 +1,15 @@
 name: Java CI
 
-on: [push]
+on: [push, pull_request]
 
 jobs:
   build:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up JDK 11
-        uses: actions/setup-java@v2
+        uses: actions/setup-java@v3
         with:
           java-version: '11'
           distribution: 'adopt'

README.md

@@ -9,7 +9,7 @@ tabula-java [![Build Status](https://travis-ci.org/tabulapdf/tabula-java.svg?bra
 
 Download a version of the tabula-java's jar, with all dependencies included, that works on Mac, Windows and Linux from our [releases page](../../releases).
 
-## Usage Examples
+## Commandline Usage Examples
 
 `tabula-java` provides a command line application:
 
@@ -81,6 +81,47 @@ JVM start-up time is a lot of the cost of the `tabula` command, so if you're try
  - writing your own program in any JVM language (Java, JRuby, Scala) that imports tabula-java.
  - waiting for us to implement an API/server-style system (it's on the [roadmap](https://github.com/tabulapdf/tabula-api))
 
+## API Usage Examples
+
+A simple Java code example which extracts all rows and cells from all tables of all pages of a PDF document:
+
+```java
+InputStream in = this.getClass().getResourceAsStream("my.pdf");
+try (PDDocument document = PDDocument.load(in)) {
+    SpreadsheetExtractionAlgorithm sea = new SpreadsheetExtractionAlgorithm();
+    PageIterator pi = new ObjectExtractor(document).extract();
+    while (pi.hasNext()) {
+        // iterate over the pages of the document
+        Page page = pi.next();
+        List<Table> table = sea.extract(page);
+        // iterate over the tables of the page
+        for(Table tables: table) {
+            List<List<RectangularTextContainer>> rows = tables.getRows();
+            // iterate over the rows of the table
+            for (List<RectangularTextContainer> cells : rows) {
+                // print all column-cells of the row plus linefeed
+                for (RectangularTextContainer content : cells) {
+                    // Note: Cell.getText() uses \r to concat text chunks
+                    String text = content.getText().replace("\r", " ");
+                    System.out.print(text + "|");
+                }
+                System.out.println();
+            }
+        }
+    }
+}
+```
+
+
+For more detail information check the Javadoc. 
+The Javadoc API documentation can be generated (see also '_Building from Source_' section) via
+
+```
+mvn javadoc:javadoc
+```
+
+which generates the HTML files to directory ```target/site/apidocs/```
+
 ## Building from Source
 
 Clone this repo and run: