File size: 10,386 Bytes
b80cddf
 
 
 
 
 
 
01768eb
 
 
 
b80cddf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a86d063
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b80cddf
 
a86d063
b80cddf
 
 
 
 
a86d063
b80cddf
 
 
a86d063
 
b80cddf
a86d063
b80cddf
 
a86d063
 
 
 
 
 
 
 
b80cddf
 
 
a86d063
b80cddf
a86d063
 
 
b80cddf
a86d063
 
 
b80cddf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
"""
PDF Processing utilities for extracting and chunking text from PDF files
"""
import os
from typing import List, Dict
import PyPDF2
import pdfplumber
try:
    from langchain_text_splitters import RecursiveCharacterTextSplitter
except ImportError:
    from langchain.text_splitter import RecursiveCharacterTextSplitter
from config.model_config import config

class PDFProcessor:
    """Handle PDF text extraction and processing"""
    
    def __init__(self):
        self.text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=config.CHUNK_SIZE,
            chunk_overlap=config.CHUNK_OVERLAP,
            length_function=len,
            separators=["\n\n", "\n", " ", ""]
        )
    
    def extract_text_from_pdf(self, pdf_path: str, method: str = "pdfplumber") -> str:
        """
        Extract text from PDF file
        
        Args:
            pdf_path: Path to PDF file
            method: Extraction method ('pypdf2' or 'pdfplumber')
            
        Returns:
            Extracted text as string
        """
        text = ""
        
        try:
            if method == "pdfplumber":
                text = self._extract_with_pdfplumber(pdf_path)
            else:
                text = self._extract_with_pypdf2(pdf_path)
        except Exception as e:
            print(f"Error extracting text from {pdf_path}: {e}")
            # Fallback to alternative method
            if method == "pdfplumber":
                text = self._extract_with_pypdf2(pdf_path)
            else:
                text = self._extract_with_pdfplumber(pdf_path)
        
        return text
    
    def _extract_with_pypdf2(self, pdf_path: str) -> str:
        """Extract text using PyPDF2"""
        text = ""
        with open(pdf_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            for page in pdf_reader.pages:
                text += page.extract_text() + "\n"
        return text
    
    def _extract_with_pdfplumber(self, pdf_path: str) -> str:
        """Extract text using pdfplumber (better for complex PDFs)"""
        text = ""
        with pdfplumber.open(pdf_path) as pdf:
            for page in pdf.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + "\n"
        return text
    
    def chunk_text(self, text: str) -> List[str]:
        """
        Split text into chunks
        
        Args:
            text: Input text to chunk
            
        Returns:
            List of text chunks
        """
        chunks = self.text_splitter.split_text(text)
        return chunks
    
    def extract_with_structure(self, pdf_path: str) -> Dict:
        """
        Extract text with page and paragraph structure
        
        Args:
            pdf_path: Path to PDF file
            
        Returns:
            Dictionary with structured content including pages and paragraphs
        """
        structured_content = {
            "pages": [],
            "paragraphs": [],
            "full_text": ""
        }
        
        try:
            with pdfplumber.open(pdf_path) as pdf:
                paragraph_id = 0
                
                for page_num, page in enumerate(pdf.pages, start=1):
                    page_text = page.extract_text()
                    if not page_text:
                        continue
                    
                    # Split into paragraphs (double newline or significant whitespace)
                    raw_paragraphs = page_text.split('\n\n')
                    page_paragraphs = []
                    
                    for para_text in raw_paragraphs:
                        para_text = para_text.strip()
                        if len(para_text) > 20:  # Ignore very short fragments
                            paragraph_id += 1
                            paragraph_data = {
                                "id": f"para_{paragraph_id}",
                                "page": page_num,
                                "text": para_text,
                                "char_start": len(structured_content["full_text"]),
                                "char_end": len(structured_content["full_text"]) + len(para_text)
                            }
                            page_paragraphs.append(paragraph_data)
                            structured_content["paragraphs"].append(paragraph_data)
                            structured_content["full_text"] += para_text + "\n\n"
                    
                    structured_content["pages"].append({
                        "page_num": page_num,
                        "text": page_text,
                        "paragraphs": page_paragraphs
                    })
        
        except Exception as e:
            print(f"Error extracting structured content: {e}")
            # Fallback to simple extraction
            text = self.extract_text_from_pdf(pdf_path)
            structured_content["full_text"] = text
            structured_content["paragraphs"] = [{
                "id": "para_1",
                "page": 1,
                "text": text,
                "char_start": 0,
                "char_end": len(text)
            }]
        
        return structured_content
    
    def generate_html_preview(self, structured_content: Dict, filename: str) -> str:
        """
        Generate HTML representation of PDF for viewer
        
        Args:
            structured_content: Structured content from extract_with_structure
            filename: Name of the PDF file
            
        Returns:
            HTML string
        """
        html = f"""
        <div class="document-content" data-filename="{filename}">
            <div class="document-header">
                <h3>📄 {filename}</h3>
                <p class="doc-meta">{len(structured_content['pages'])} halaman • {len(structured_content['paragraphs'])} paragraf</p>
            </div>
        """
        
        for page in structured_content["pages"]:
            html += f"""
            <div class="pdf-page" data-page="{page['page_num']}">
                <div class="page-number">Halaman {page['page_num']}</div>
            """
            
            for para in page["paragraphs"]:
                html += f"""
                <p class="paragraph" id="{para['id']}" data-page="{para['page']}">
                    {para['text']}
                </p>
                """
            
            html += "</div>"
        
        html += "</div>"
        return html
    
    def chunk_text_with_metadata(self, structured_content: Dict) -> List[Dict]:
        """
        Split text into chunks with metadata about source location
        
        Args:
            structured_content: Structured content from extract_with_structure
            
        Returns:
            List of dictionaries with chunk text and metadata
        """
        # Get chunks from the splitter
        text_chunks = self.text_splitter.split_text(structured_content["full_text"])
        
        chunks_with_metadata = []
        
        for i, chunk_text in enumerate(text_chunks):
            # Find which paragraphs this chunk overlaps with
            chunk_start = structured_content["full_text"].find(chunk_text)
            chunk_end = chunk_start + len(chunk_text)
            
            # Find overlapping paragraphs
            related_paragraphs = []
            related_pages = set()
            
            for para in structured_content["paragraphs"]:
                # Check if chunk overlaps with paragraph
                if not (chunk_end < para["char_start"] or chunk_start > para["char_end"]):
                    related_paragraphs.append(para["id"])
                    related_pages.add(para["page"])
            
            chunks_with_metadata.append({
                "text": chunk_text,
                "chunk_index": i,
                "paragraph_ids": related_paragraphs,
                "pages": sorted(list(related_pages)),
                "char_start": chunk_start,
                "char_end": chunk_end
            })
        
        return chunks_with_metadata
    
    def process_pdf(self, pdf_path: str) -> Dict:
        """
        Complete processing pipeline: extract and chunk PDF with structure
        
        Args:
            pdf_path: Path to PDF file
            
        Returns:
            Dictionary with filename, text, chunks, and structured content
        """
        filename = os.path.basename(pdf_path)
        
        # Extract structured content
        structured_content = self.extract_with_structure(pdf_path)
        
        if not structured_content["full_text"].strip():
            raise ValueError(f"No text extracted from {filename}")
        
        # Generate HTML preview
        html_preview = self.generate_html_preview(structured_content, filename)
        
        # Chunk text with metadata
        chunks_with_metadata = self.chunk_text_with_metadata(structured_content)
        
        # Extract just the text for backward compatibility
        chunks = [c["text"] for c in chunks_with_metadata]
        
        return {
            "filename": filename,
            "full_text": structured_content["full_text"],
            "chunks": chunks,
            "chunks_metadata": chunks_with_metadata,
            "structured_content": structured_content,
            "html_preview": html_preview,
            "num_chunks": len(chunks),
            "total_chars": len(structured_content["full_text"]),
            "num_pages": len(structured_content["pages"]),
            "num_paragraphs": len(structured_content["paragraphs"])
        }
    
    def get_pdf_info(self, pdf_path: str) -> Dict:
        """
        Get metadata about PDF file
        
        Args:
            pdf_path: Path to PDF file
            
        Returns:
            Dictionary with PDF metadata
        """
        info = {
            "filename": os.path.basename(pdf_path),
            "file_size": os.path.getsize(pdf_path),
            "num_pages": 0
        }
        
        try:
            with open(pdf_path, 'rb') as file:
                pdf_reader = PyPDF2.PdfReader(file)
                info["num_pages"] = len(pdf_reader.pages)
        except Exception as e:
            print(f"Error getting PDF info: {e}")
        
        return info