SimpleChatTC:SimpleProxy:Move pdf logic into its own module

Author: hanishkvc

tools/server/public_simplechat/local.tools/pdfmagic.py

@@ -0,0 +1,58 @@
+# Helper to manage pdf related requests
+# by Humans for All
+
+import urllib.parse
+import urlvalidator as uv
+import simpleproxy as root
+
+
+def process_pdf2text(url: str, startPN: int, endPN: int):
+    import pypdf
+    import io
+    gotVU = uv.validate_url(url, "HandlePdf2Text")
+    if not gotVU.callOk:
+        return { 'status': gotVU.statusCode, 'msg': gotVU.statusMsg }
+    urlParts = urllib.parse.urlparse(url)
+    fPdf = open(urlParts.path, 'rb')
+    dPdf = fPdf.read()
+    tPdf = ""
+    oPdf = pypdf.PdfReader(io.BytesIO(dPdf))
+    if (startPN < 0):
+        startPN = 0
+    if (endPN < 0) or (endPN >= len(oPdf.pages)):
+        endPN = len(oPdf.pages)-1
+    for i in range(startPN, endPN+1):
+        pd = oPdf.pages[i]
+        tPdf = tPdf + pd.extract_text()
+    return { 'status': 200, 'msg': "Pdf2Text Response follows", 'data': tPdf }
+
+
+def handle_pdf2text(ph: root.ProxyHandler, pr: urllib.parse.ParseResult):
+    """
+    Handle requests to pdf2text path, which is used to extract plain text
+    from the specified pdf file.
+    """
+    queryParams = urllib.parse.parse_qs(pr.query)
+    url = queryParams['url'][0]
+    startP = queryParams['startPageNumber'][0]
+    if startP:
+        startP = int(startP)
+    else:
+        startP = -1
+    endP = queryParams['endPageNumber'][0]
+    if endP:
+        endP = int(endP)
+    else:
+        endP = -1
+    print(f"INFO:HandlePdf2Text:Processing:{url}:{startP}:{endP}...")
+    gotP2T = process_pdf2text(url, startP, endP)
+    if (gotP2T['status'] != 200):
+        ph.send_error(gotP2T['status'], gotP2T['msg'] )
+        return
+    ph.send_response(gotP2T['status'], gotP2T['msg'])
+    ph.send_header('Content-Type', 'text/text')
+    # Add CORS for browser fetch, just in case
+    ph.send_header('Access-Control-Allow-Origin', '*')
+    ph.end_headers()
+    print(f"INFO:HandlePdf2Text:ExtractedText:{url}...")
+    ph.wfile.write(gotP2T['data'].encode('utf-8'))

tools/server/public_simplechat/local.tools/simpleproxy.py

@@ -27,6 +27,7 @@
 import time
 import urlvalidator as uv
 from typing import Callable
+import pdfmagic as mPdf
 
 
 gMe = {
@@ -136,7 +137,7 @@ def do_GET(self):
             case '/urltext':
                 self.auth_and_run(pr, handle_urltext)
             case '/pdf2text':
-                self.auth_and_run(pr, handle_pdf2text)
+                self.auth_and_run(pr, mPdf.handle_pdf2text)
             case '/aum':
                 handle_aum(self, pr)
             case _:
@@ -358,58 +359,6 @@ def handle_urltext(ph: ProxyHandler, pr: urllib.parse.ParseResult):
         ph.send_error(502, f"WARN:UrlTextFailed:{exc}")
 
 
-def process_pdf2text(url: str, startPN: int, endPN: int):
-    import pypdf
-    import io
-    gotVU = uv.validate_url(url, "HandlePdf2Text")
-    if not gotVU.callOk:
-        return { 'status': gotVU.statusCode, 'msg': gotVU.statusMsg }
-    urlParts = urllib.parse.urlparse(url)
-    fPdf = open(urlParts.path, 'rb')
-    dPdf = fPdf.read()
-    tPdf = ""
-    oPdf = pypdf.PdfReader(io.BytesIO(dPdf))
-    if (startPN < 0):
-        startPN = 0
-    if (endPN < 0) or (endPN >= len(oPdf.pages)):
-        endPN = len(oPdf.pages)-1
-    for i in range(startPN, endPN+1):
-        pd = oPdf.pages[i]
-        tPdf = tPdf + pd.extract_text()
-    return { 'status': 200, 'msg': "Pdf2Text Response follows", 'data': tPdf }
-
-
-def handle_pdf2text(ph: ProxyHandler, pr: urllib.parse.ParseResult):
-    """
-    Handle requests to pdf2text path, which is used to extract plain text
-    from the specified pdf file.
-    """
-    queryParams = urllib.parse.parse_qs(pr.query)
-    url = queryParams['url'][0]
-    startP = queryParams['startPageNumber'][0]
-    if startP:
-        startP = int(startP)
-    else:
-        startP = -1
-    endP = queryParams['endPageNumber'][0]
-    if endP:
-        endP = int(endP)
-    else:
-        endP = -1
-    print(f"INFO:HandlePdf2Text:Processing:{url}:{startP}:{endP}...")
-    gotP2T = process_pdf2text(url, startP, endP)
-    if (gotP2T['status'] != 200):
-        ph.send_error(gotP2T['status'], gotP2T['msg'] )
-        return
-    ph.send_response(gotP2T['status'], gotP2T['msg'])
-    ph.send_header('Content-Type', 'text/text')
-    # Add CORS for browser fetch, just in case
-    ph.send_header('Access-Control-Allow-Origin', '*')
-    ph.end_headers()
-    print(f"INFO:HandlePdf2Text:ExtractedText:{url}...")
-    ph.wfile.write(gotP2T['data'].encode('utf-8'))
-
-
 
 def load_config():
     """