feature(read pdf paper then write summary):

add a func called readPdf in toolbox, which can read pdf paper to str. then use bs4.BeautifulSoup to clean content.

crazy_functions/读文章写摘要.py

@@ -1,14 +1,19 @@
 from predict import predict_no_ui
-from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down
+from toolbox import CatchException, report_execption, write_results_to_file, predict_no_ui_but_counting_down, readPdf
 fast_debug = False
+from bs4 import BeautifulSoup
 
 
 def 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt):
     import time, glob, os
     print('begin analysis on:', file_manifest)
     for index, fp in enumerate(file_manifest):
+        if ".tex" in fp:
             with open(fp, 'r', encoding='utf-8') as f:
                 file_content = f.read()
+        if ".pdf" in fp:
+            file_content = readPdf(fp)
+            file_content = BeautifulSoup(''.join(file_content), features="lxml").body.text.encode('gbk', 'ignore').decode('gbk')
 
         prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
         i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
@@ -60,11 +65,12 @@ def 读文章写摘要(txt, top_p, temperature, chatbot, history, systemPromptTx
         report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield chatbot, history, '正常'
         return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] # + \
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)] # + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或pdf文件: {txt}")
         yield chatbot, history, '正常'
         return
     yield from 解析Paper(file_manifest, project_folder, top_p, temperature, chatbot, history, systemPromptTxt)

functional_crazy.py

@@ -30,7 +30,7 @@ def get_crazy_functionals():
             "Color": "stop",    # 按钮颜色
             "Function": 解析一个C项目
         },
-        "读tex论文写摘要": {
+        "读tex or pdf论文写摘要": {
             "Color": "stop",    # 按钮颜色
             "Function": 读文章写摘要
         },

requirements.txt

@@ -1,3 +1,10 @@
 gradio>=3.23
-requests[socks]
-mdtex2html
+requests[socks]~=2.28.2
+mdtex2html~=1.2.0
+Markdown~=3.4.3
+latex2mathml~=3.75.1
+bs4~=0.0.1
+lxml~=4.6.4
+beautifulsoup4~=4.12.0
+numpy~=1.24.2
+pdfminer.six

toolbox.py

@@ -1,6 +1,14 @@
 import markdown, mdtex2html, threading, importlib, traceback
 from show_math import convert as convert_math
 from functools import wraps
+import pdfminer
+from pdfminer.pdfparser import PDFParser
+from pdfminer.pdfdocument import PDFDocument
+from pdfminer.pdfpage import PDFPage, PDFTextExtractionNotAllowed
+from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
+from pdfminer.pdfdevice import PDFDevice
+from pdfminer.layout import LAParams
+from pdfminer.converter import PDFPageAggregator
 
 def predict_no_ui_but_counting_down(i_say, i_say_show_user, chatbot, top_p, temperature, history=[], sys_prompt=''):
     """
@@ -236,3 +244,51 @@ def clear_line_break(txt):
     txt = txt.replace('  ', ' ')
     txt = txt.replace('  ', ' ')
     return txt
+
+def readPdf(pdfPath):
+    """
+    读取pdf文件，返回文本内容
+    """
+    fp = open(pdfPath, 'rb')
+
+    # Create a PDF parser object associated with the file object
+    parser = PDFParser(fp)
+
+    # Create a PDF document object that stores the document structure.
+    # Password for initialization as 2nd parameter
+    document = PDFDocument(parser)
+    # Check if the document allows text extraction. If not, abort.
+    if not document.is_extractable:
+        raise PDFTextExtractionNotAllowed
+
+    # Create a PDF resource manager object that stores shared resources.
+    rsrcmgr = PDFResourceManager()
+
+    # Create a PDF device object.
+    # device = PDFDevice(rsrcmgr)
+
+    # BEGIN LAYOUT ANALYSIS.
+    # Set parameters for analysis.
+    laparams = LAParams(
+        char_margin=10.0,
+        line_margin=0.2,
+        boxes_flow=0.2,
+        all_texts=False,
+    )
+    # Create a PDF page aggregator object.
+    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
+    # Create a PDF interpreter object.
+    interpreter = PDFPageInterpreter(rsrcmgr, device)
+
+    # loop over all pages in the document
+    outTextList = []
+    for page in PDFPage.create_pages(document):
+        # read the page into a layout object
+        interpreter.process_page(page)
+        layout = device.get_result()
+        for obj in layout._objs:
+            if isinstance(obj, pdfminer.layout.LTTextBoxHorizontal):
+                # print(obj.get_text())
+                outTextList.append(obj.get_text())
+
+    return outTextList