chore: code fix for pdf loader and tests

.gitignore

@@ -1 +1,7 @@
 /target
+
+# resources 
+.resource
+
+# files
+main.rs 

README.md

@@ -36,6 +36,7 @@ These are some chunking strategy examples:
 
 - [Chunking by words](/examples/chunk_by_words.rs) - Chunk your documents/texts by number of words. 
 - [Chunking by characters](/examples/chunk_by_chars.rs) - Chunk your documents/text by number of characters.
+- [Chunk PDF document](/examples/chunk_document.rs) - Chunk your pdf documents by words/characters.
 
 Run them using the cargo command like:
 ```bash

src/loader/pdf.rs

@@ -17,8 +17,8 @@ impl BaseLoader<Result<String>> for PDFLoader {
         let pages = doc.get_pages();
         for (i, _) in pages.iter().enumerate() {
             let page_number = (i + 1) as u32;
-            let text = doc.extract_text(&[page_number]);
-            content.push_str(text.unwrap().as_str());
+            let text = doc.extract_text(&[page_number]).unwrap();
+            content.push_str(text.as_str());
         }
         Ok(content)
     }

tests/chunker_tests.rs

@@ -12,13 +12,13 @@ fn test_character_chunker() {
     let input_text = loader
         .load_from_file("tests/test_files/sample_doc.pdf")
         .unwrap();
-    let chunk_size = 3000;
+    let chunk_size = 1000;
     let overlap = 50;
     let chunks = char_chunker
         .chunk_text(&input_text, chunk_size, overlap)
         .unwrap();
     dbg!(chunks.len());
-    assert_eq!(58, chunks.len());
+    assert_eq!(5, chunks.len());
 }
 
 #[test]
@@ -35,5 +35,5 @@ fn test_word_chunker() {
         .chunk_text(&input_text, chunk_size, overlap)
         .unwrap();
     dbg!(&chunks);
-    assert_eq!(11060, chunks[0].content.len());
+    assert_eq!(1627, chunks[0].content.len());
 }