fix RAGFlowPdfParser AttributeError: 'PdfReader' object has no attribute 'close' err (#6859)

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

@@ -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
+
+                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)
 
-            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")