happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SimpleChatTC:SimpleProxy:Pdf2Text cleanup page number handling 

Its not necessary to request a page number range always.

Take care of page number starting from 1 and underlying data having
0 as the starting index
This commit is contained in:
hanishkvc 2025-11-02 18:30:11 +05:30
parent d012d127bf
commit a3beacf16a
1 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
tools/server/public_simplechat/local.tools/pdfmagic.py
View File

@ -10,6 +10,16 @@ if TYPE_CHECKING:
def process_pdf2text(url: str, startPN: int, endPN: int): def process_pdf2text(url: str, startPN: int, endPN: int):
"""
Extract textual content from given pdf.
* Validate the got url.
* Extract textual contents of the pdf from given start page number to end page number (inclusive).
* if -1 | 0 is specified wrt startPN, the actual starting page number (rather 1) will be used.
* if -1 | 0 is specified wrt endPN, the actual ending page number will be used.
NOTE: Page numbers start from 1, while the underlying list data structure index starts from 0
"""
import pypdf import pypdf
import io import io
gotVU = uv.validate_url(url, "HandlePdf2Text") gotVU = uv.validate_url(url, "HandlePdf2Text")
@ -20,12 +30,12 @@ def process_pdf2text(url: str, startPN: int, endPN: int):
dPdf = fPdf.read() dPdf = fPdf.read()
tPdf = "" tPdf = ""
oPdf = pypdf.PdfReader(io.BytesIO(dPdf)) oPdf = pypdf.PdfReader(io.BytesIO(dPdf))
if (startPN < 0): if (startPN <= 0):
startPN = 0 startPN = 1
if (endPN < 0) or (endPN >= len(oPdf.pages)): if (endPN <= 0) or (endPN > len(oPdf.pages)):
endPN = len(oPdf.pages)-1 endPN = len(oPdf.pages)
for i in range(startPN, endPN+1): for i in range(startPN, endPN+1):
pd = oPdf.pages[i] pd = oPdf.pages[i-1]
tPdf = tPdf + pd.extract_text() tPdf = tPdf + pd.extract_text()
return { 'status': 200, 'msg': "Pdf2Text Response follows", 'data': tPdf } return { 'status': 200, 'msg': "Pdf2Text Response follows", 'data': tPdf }
@ -37,16 +47,12 @@ def handle_pdf2text(ph: 'ProxyHandler', pr: urllib.parse.ParseResult):
""" """
queryParams = urllib.parse.parse_qs(pr.query) queryParams = urllib.parse.parse_qs(pr.query)
url = queryParams['url'][0] url = queryParams['url'][0]
startP = queryParams['startPageNumber'][0] startP = queryParams.get('startPageNumber', -1)
if startP: if isinstance(startP, list):
startP = int(startP) startP = int(startP[0])
else: endP = queryParams.get('endPageNumber', -1)
startP = -1 if isinstance(endP, list):
endP = queryParams['endPageNumber'][0] endP = int(endP[0])
if endP:
endP = int(endP)
else:
endP = -1
print(f"INFO:HandlePdf2Text:Processing:{url}:{startP}:{endP}...") print(f"INFO:HandlePdf2Text:Processing:{url}:{startP}:{endP}...")
gotP2T = process_pdf2text(url, startP, endP) gotP2T = process_pdf2text(url, startP, endP)
if (gotP2T['status'] != 200): if (gotP2T['status'] != 200):