File size: 10,358 Bytes
7bd9199
 
 
f66027e
266e2a4
7bd9199
 
 
f66027e
cf34c19
7bd9199
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc472fa
 
 
7bd9199
 
 
dc472fa
 
 
 
 
 
 
 
 
 
 
7bd9199
 
dc472fa
 
 
 
 
 
 
 
 
 
 
 
 
 
7bd9199
 
dc472fa
7bd9199
 
 
 
dc472fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7bd9199
dc472fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7bd9199
dc472fa
 
 
 
 
 
 
 
 
 
7bd9199
dc472fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7bd9199
 
 
 
 
 
 
ab6174c
266e2a4
ab6174c
 
 
 
 
266e2a4
 
 
 
 
 
 
ab6174c
 
266e2a4
 
 
ab6174c
 
 
 
 
 
 
 
 
 
 
 
 
 
266e2a4
 
 
 
 
 
 
 
cf34c19
266e2a4
 
 
 
 
 
 
 
7bd9199
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import asyncio
import io
import json
import os
import uuid
import fitz
from openpyxl import load_workbook
import markdown2
import subprocess
from pathlib import Path

class FileClient:
    def __init__(self):
        pass

    async def __aenter__(self):
        return self
    
    async def __aexit__(self, exc_type, exc_value, traceback):
        pass

    async def extract_from_pdf(self, file_bytes: io.BytesIO):
        doc = fitz.open(stream=file_bytes, filetype="pdf")

        layout_data = {
            "metadata": doc.metadata,
            "page_count": len(doc),
            "pages": []
        }

        all_headers = []
        all_footers = []

        for page_num, page in enumerate(doc):
            blocks = page.get_text("dict")["blocks"]
            page_content = []
            text_blocks = []
            header_blocks = []
            footer_blocks = []
            body_blocks = []

            page_rect = page.rect
            media_box = page.mediabox if hasattr(page, 'mediabox') else page_rect
            crop_box = page.cropbox

            header_region = (page_rect.y0, page_rect.y0 + (page_rect.height * 0.2))
            footer_region = (page_rect.y1 - (page_rect.height * 0.2), page_rect.y1)

            for block in blocks:
                if "lines" in block and block.get("bbox"):
                    block_bbox = block["bbox"]
                    
                    is_header = block_bbox[1] >= header_region[0] and block_bbox[3] <= header_region[1]
                    is_footer = block_bbox[1] >= footer_region[0] and block_bbox[3] <= footer_region[1]

                    if is_header:
                        header_blocks.append(block_bbox)
                    elif is_footer:
                        footer_blocks.append(block_bbox)
                    else:
                        body_blocks.append(block_bbox)
                        text_blocks.append(block_bbox)

                    for line in block["lines"]:
                        for span in line["spans"]:
                            content_item = {
                                "text": span["text"],
                                "font": span["font"],
                                "size": span["size"],
                                "color": span.get("color", None),
                                "flags": span.get("flags", None),
                                "is_header": is_header,
                                "is_footer": is_footer
                            }
                            page_content.append(content_item)

            if body_blocks:
                min_x = min(block[0] for block in body_blocks)
                min_y = min(block[1] for block in body_blocks)
                max_x = max(block[2] for block in body_blocks)
                max_y = max(block[3] for block in body_blocks)
                
                margin_left = (min_x - page_rect.x0) / 72
                margin_top = (min_y - page_rect.y0) / 72
                margin_right = (page_rect.x1 - max_x) / 72
                margin_bottom = (page_rect.y1 - max_y) / 72
            else:
                margin_left = margin_top = margin_right = margin_bottom = 0

            crop_margin_left = (crop_box.x0 - media_box.x0) / 72
            crop_margin_top = (crop_box.y0 - media_box.y0) / 72
            crop_margin_right = (media_box.x1 - crop_box.x1) / 72
            crop_margin_bottom = (media_box.y1 - crop_box.y1) / 72

            header_height = 0
            footer_height = 0
            if header_blocks:
                header_min_y = min(block[1] for block in header_blocks)
                header_max_y = max(block[3] for block in header_blocks)
                header_height = (header_max_y - header_min_y) / 72
            if footer_blocks:
                footer_min_y = min(block[1] for block in footer_blocks)
                footer_max_y = max(block[3] for block in footer_blocks)
                footer_height = (footer_max_y - footer_min_y) / 72

            header_text = ""
            footer_text = ""
            for item in page_content:
                if item["is_header"]:
                    header_text += item["text"] + " "
                elif item["is_footer"]:
                    footer_text += item["text"] + " "

            header_text = header_text.strip()
            footer_text = footer_text.strip()

            if header_text:
                all_headers.append(header_text)
            if footer_text:
                all_footers.append(footer_text)

            page_data = {
                "page_number": page_num + 1,
                "width": page_rect.width,
                "height": page_rect.height,
                "margin_top": f"{round(margin_top, 1)} inches",
                "margin_left": f"{round(margin_left, 1)} inches",
                "margin_right": f"{round(margin_right, 1)} inches",
                "margin_bottom": f"{round(margin_bottom, 1)} inches",
                "header_height": f"{header_height} inches",
                "footer_height": f"{footer_height} inches",
                "has_header": len(header_blocks) > 0,
                "has_footer": len(footer_blocks) > 0,
                "content": page_content
            }

            if page_num == 0:
                page_data["is_first_page"] = True

            layout_data["pages"].append(page_data)

        if all_headers:
            unique_headers = set(all_headers)
            layout_data["header_analysis"] = {
                "total_pages_with_headers": len(all_headers),
                "unique_headers": len(unique_headers),
                "is_header_consistent": len(unique_headers) == 1 if all_headers else False
            }

        if all_footers:
            unique_footers = set(all_footers)
            layout_data["footer_analysis"] = {
                "total_pages_with_footers": len(all_footers),
                "unique_footers": len(unique_footers),
                "is_footer_consistent": len(unique_footers) == 1 if all_footers else False
            }

        return layout_data

    async def extrcat_from_word(self, file_bytes: io.BytesIO):
        data = {
            "file_type": "Word Document"
        }

        file_id = str(uuid.uuid4())
        work_dir = f"/files/{file_id}"
        os.makedirs(work_dir, exist_ok=True)

        docx_path = os.path.join(work_dir, "input.docx")
        pdf_path = os.path.join(work_dir, "input.pdf")

        try:
            with open(docx_path, "wb") as f:
                f.write(file_bytes.getvalue())

            env = os.environ.copy()
            env.update({
                "HOME": work_dir,
                "UserInstallation": f"file://{work_dir}",
                "SAL_USE_VCLPLUGIN": "svp"
            })

            cmd = [
                "libreoffice",
                "--headless",
                "--nologo",
                "--nofirststartwizard",
                "--convert-to", "pdf",
                "--outdir", work_dir,
                docx_path
            ]

            await asyncio.to_thread(
                subprocess.run,
                cmd,
                check=True,
                capture_output=True,
                env=env
            )

            with open(pdf_path, "rb") as f:
                pdf_bytes = io.BytesIO(f.read())

            data["data"] = await self.extract_from_pdf(file_bytes=pdf_bytes)
        
            return data

        finally:
            for file_path in [docx_path, pdf_path]:
                if os.path.exists(file_path):
                    os.remove(file_path)


    async def extract_from_excel(self, file_bytes: io.BytesIO):
        wb = load_workbook(file_bytes, data_only=True)

        sheets_data = []
        for sheet in wb.worksheets:
            sheet_info = {
                "sheet_name": sheet.title,
                "cells": []
            }
            for row in sheet.iter_rows():
                for cell in row:
                    if cell.value is None:
                        continue

                    cell_info = {
                        "coordinate": cell.coordinate,
                        "value": cell.value,
                    }

                    if cell.font:
                        if cell.font.name:
                            cell_info["font_name"] = cell.font.name
                        if cell.font.size:
                            cell_info["font_size"] = cell.font.size
                        if cell.font.bold:
                            cell_info["bold"] = True
                        if cell.font.italic:
                            cell_info["italic"] = True
                        if cell.font.underline:
                            cell_info["underline"] = True

                    if cell.alignment:
                        if cell.alignment.horizontal:
                            cell_info["horizontal_align"] = cell.alignment.horizontal
                        if cell.alignment.vertical:
                            cell_info["vertical_align"] = cell.alignment.vertical
                        if cell.alignment.wrap_text:
                            cell_info["wrap_text"] = True

                    if cell.fill and cell.fill.start_color and cell.fill.start_color.rgb:
                        color = cell.fill.start_color.rgb
                        if color != "00000000":  
                            cell_info["fill_color"] = color

                    cell_info = {k: v for k, v in cell_info.items() if v is not None}
                    sheet_info["cells"].append(cell_info)

            sheets_data.append(sheet_info)

        final_data = {
            "sheets": sheets_data
        }
        return final_data

    async def extract_from_json(self, file_bytes: io.BytesIO):
        data = json.load(file_bytes)
        return data

    async def extrcat_from_md(self, file_bytes: io.BytesIO):
        data = {
            "file_type": "Markdown"
        }
        md_bytes = file_bytes.getvalue().decode("utf-8")
        data["data"] = markdown2.markdown(md_bytes)
        return data

    async def extract_from_txt(self, file_bytes: io.BytesIO):
        data = file_bytes.getvalue().decode("utf-8")
        return data

    async def extract_from_csv(self, file_bytes: io.BytesIO):
        data = file_bytes.getvalue().decode("utf-8")
        return data