From 53c653b099955696b144832d7d6055bb15823b2d Mon Sep 17 00:00:00 2001 From: gsmini Date: Mon, 14 Apr 2025 09:40:13 +0800 Subject: [PATCH] fix RAGFlowPdfParser AttributeError: 'PdfReader' object has no attribute 'close' err (#6859) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit i use PdfParser in local(refer to this case: https://github.com/infiniflow/ragflow/blob/main/rag/app/paper.py) like this: ``` import re import openpyxl from ragflow.api.db import ParserType from ragflow.rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, \ title_frequency, \ tokenize_chunks from ragflow.rag.utils import num_tokens_from_string from ragflow.deepdoc.parser import PdfParser, ExcelParser, DocxParser,PlainParser def logger(prog=None, msg=""): print(msg) class Pdf(PdfParser): def __init__(self): self.model_speciess = ParserType.MANUAL.value super().__init__() def __call__(self, filename, binary=None, from_page=0, to_page=100000, zoomin=3, callback=None): from timeit import default_timer as timer start = timer() callback(msg="OCR is running...") self.__images__( filename if not binary else binary, zoomin, from_page, to_page, callback ) callback(msg="OCR finished.") print("OCR:", timer() - start) self._layouts_rec(zoomin) callback(0.65, "Layout analysis finished.") print("layouts:", timer() - start) self._table_transformer_job(zoomin) callback(0.67, "Table analysis finished.") self._text_merge() tbls = self._extract_table_figure(True, zoomin, True, True) self._concat_downward() self._filter_forpages() callback(0.68, "Text merging finished") # clean mess for b in self.boxes: b["text"] = re.sub(r"([\t 　]|\u3000){2,}", " ", b["text"].strip()) return [(b["text"], b.get("layout_no", ""), self.get_position(b, zoomin)) for i, b in enumerate(self.boxes)], tbls ``` show err like this: ``` File "xxxxx/third_party/ragflow/deepdoc/parser/pdf_parser.py", line 1039, in __images__ self.pdf.close() AttributeError: 'PdfReader' object has no attribute 'close' ``` i found ragflow source code use `pdfplumber.open`（https://github.com/infiniflow/ragflow/blob/main/deepdoc/parser/pdf_parser.py#L1007C28-L1007C43） and replace` self.pdf `with ` pdf2_read` （from pypdf import PdfReader as pdf2_read）in line 1024 (https://github.com/infiniflow/ragflow/blob/main/deepdoc/parser/pdf_parser.py#L1024) ``` self.pdf = pdf2_read ``` --- and I found that `pdfplumber` can be used in this way： ``` file_path="xxx.pdf" res = pdfplumber.open(file_path) res.close() ``` but `pypdf.PdfReader` source code do not has `close` func, source code use like this ``` with open(stream, "rb") as fh: stream = BytesIO(fh.read()) self._stream_opened = True ``` > https://github.com/py-pdf/pypdf/blob/main/pypdf/_reader.py#L156 so I moved the `self.pdf.close` function call and fixed this problem hoping to help the project😊 --- deepdoc/parser/pdf_parser.py | 46 ++++++++++++++++++++---------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/deepdoc/parser/pdf_parser.py b/deepdoc/parser/pdf_parser.py index 029bf634..3973ce03 100644 --- a/deepdoc/parser/pdf_parser.py +++ b/deepdoc/parser/pdf_parser.py @@ -1004,38 +1004,42 @@ class RAGFlowPdfParser: start = timer() try: with sys.modules[LOCK_KEY_pdfplumber]: - self.pdf = pdfplumber.open(fnm) if isinstance( - fnm, str) else pdfplumber.open(BytesIO(fnm)) - self.page_images = [p.to_image(resolution=72 * zoomin).annotated for i, p in - enumerate(self.pdf.pages[page_from:page_to])] - try: - self.page_chars = [[c for c in page.dedupe_chars().chars if self._has_color(c)] for page in self.pdf.pages[page_from:page_to]] - except Exception as e: - logging.warning(f"Failed to extract characters for pages {page_from}-{page_to}: {str(e)}") - self.page_chars = [[] for _ in range(page_to - page_from)] # If failed to extract, using empty list instead. + with (pdfplumber.open(fnm) if isinstance(fnm, str) else pdfplumber.open(BytesIO(fnm))) as pdf: + self.pdf = pdf + self.page_images = [p.to_image(resolution=72 * zoomin).annotated for i, p in + enumerate(self.pdf.pages[page_from:page_to])] + + try: + self.page_chars = [[c for c in page.dedupe_chars().chars if self._has_color(c)] for page in self.pdf.pages[page_from:page_to]] + except Exception as e: + logging.warning(f"Failed to extract characters for pages {page_from}-{page_to}: {str(e)}") + self.page_chars = [[] for _ in range(page_to - page_from)] # If failed to extract, using empty list instead. + + self.total_page = len(self.pdf.pages) - self.total_page = len(self.pdf.pages) except Exception: logging.exception("RAGFlowPdfParser __images__") logging.info(f"__images__ dedupe_chars cost {timer() - start}s") self.outlines = [] try: - self.pdf = pdf2_read(fnm if isinstance(fnm, str) else BytesIO(fnm)) - outlines = self.pdf.outline + with (pdf2_read(fnm if isinstance(fnm, str) + else BytesIO(fnm))) as pdf: + self.pdf = pdf - def dfs(arr, depth): - for a in arr: - if isinstance(a, dict): - self.outlines.append((a["/Title"], depth)) - continue - dfs(a, depth + 1) + outlines = self.pdf.outline + def dfs(arr, depth): + for a in arr: + if isinstance(a, dict): + self.outlines.append((a["/Title"], depth)) + continue + dfs(a, depth + 1) + + dfs(outlines, 0) - dfs(outlines, 0) except Exception as e: logging.warning(f"Outlines exception: {e}") - finally: - self.pdf.close() + if not self.outlines: logging.warning("Miss outlines")