first commit for refactored project

ax3Services/docConvertService/archive_pyServer.py

@@ -0,0 +1,37 @@
+from http.server import BaseHTTPRequestHandler, HTTPServer
+import time
+from splitPdf import SplitPdf
+import logging
+
+hostName = "localhost"
+serverPort = 5050
+sp = SplitPdf()
+
+class MyServer(BaseHTTPRequestHandler):
+    
+    def do_GET(self):
+        self.send_response(200)
+        self.send_header("Content-type", "text/html")
+        self.end_headers()
+
+    def do_POST(self):
+        print('post hit')
+        content_length = int(self.headers['Content-Length']) # <--- Gets the size of data
+        print('content_length', content_length)
+        post_data = self.rfile.read(content_length) # <--- Gets the data itself
+        print('post_data', post_data)
+        logging.info("POST request,\nPath: %s\nHeaders:\n%s\n\nBody:\n%s\n",
+                str(self.path), str(self.headers), post_data.decode('utf-8'))
+        self.wfile.write("POST request for {}".format(self.path).encode('utf-8'))
+  
+if __name__ == "__main__":        
+    webServer = HTTPServer((hostName, serverPort), MyServer)
+    print("Server started http://%s:%s" % (hostName, serverPort))
+
+    try:
+        webServer.serve_forever()
+    except KeyboardInterrupt:
+        pass
+
+    webServer.server_close()
+    print("Server stopped.")

ax3Services/docConvertService/pyserv.py

@@ -0,0 +1,44 @@
+import bottle
+from bottle import run, get, post, request, route
+from bottle import HTTPResponse
+from splitPdf import SplitPdf
+from pathlib import Path
+import json
+
+def fix_environ_middleware(app):
+  def fixed_app(environ, start_response):
+    environ['wsgi.url_scheme'] = 'https'
+    environ['HTTP_X_FORWARDED_HOST'] = 'novodraft.com'
+    return app(environ, start_response)
+  return fixed_app
+
+app = bottle.default_app()
+app.wsgi = fix_environ_middleware(app.wsgi)
+sp = SplitPdf()
+suc = { 
+  'ok': True
+  }
+
+@post('/parse-new-complaint/<id>')
+def newdoc(id='test'):
+    newDir = f"{id}" # path[-1].split(".")[0]
+    print('newDir', newDir)
+    sp.make_dir(newDir)
+    path_arg = f"../Documents/Complaints/{id}.pdf"
+    print(f"../Documents/Complaints/{id}.pdf")
+    sp.split_and_convert(path_arg, newDir)
+    respBody = json.dumps({'Status': 'Success'})
+    return bottle.HTTPResponse(status=200, body=respBody)
+
+@post('/parse-new-disc-req/<id>')
+def newdoc(id='test'):
+    newDir = f"{id}"
+    print('newDir', newDir)
+    sp.make_dir(newDir)
+    path_arg = f"../Documents/Uploads/{id}.pdf"
+    print("path_arg", path_arg)
+    sp.split_and_convert(path_arg, newDir)
+    respBody = json.dumps({'Status': 'Success'})
+    return bottle.HTTPResponse(status=200, body=respBody)
+
+run(app, host='127.0.0.1', port=8081, debug=True)

ax3Services/docConvertService/splitPdf.js

@@ -0,0 +1,49 @@
+import pdf2image from "pdf2image";
+
+//The converter uses the same options as the convertPDF function
+var converter = pdf2image.compileConverter({
+  density: 200,
+  quality: 100,
+  outputFormat: "%s_page_%d",
+  outputType: "png",
+});
+
+//Converts a single pdf
+converter.convertPDF("badRogs.pdf");
+
+//Converts multiple pdfs
+//converter.convertPDFList(["example1.pdf", "example1.pdf"]);
+
+/*
+const { fromPath } = require("pdf2pic");
+const pdf = require("pdf-page-counter");
+const fs = require("fs");
+
+const split = () => {
+  const { filename } = "./badRogs.pdf";
+  const options = {
+    density: 100,
+    saveFilename: "file",
+    savePath: "./converted",
+    format: "png",
+    width: 600,
+    height: 600,
+  };
+  const storeAsImage = fromPath(`./converted/${filename}`, options);
+  let dataBuffer = fs.readFileSync(`./converted/${filename}`);
+  pdf(dataBuffer).then(function (data) {
+    for (
+      var pageToConvertAsImage = 1;
+      pageToConvertAsImage <= data.numpages;
+      pageToConvertAsImage++
+    ) {
+      storeAsImage(pageToConvertAsImage).then((resolve) => {
+        return resolve;
+      });
+    }
+    res.send({
+      filename: filename,
+    });
+  });
+};
+*/

ax3Services/docConvertService/splitPdf.py

@@ -0,0 +1,136 @@
+import os
+import uuid
+from pdf2image import convert_from_path
+from pdf2image.exceptions import (
+    PDFInfoNotInstalledError,
+    PDFPageCountError,
+    PDFSyntaxError,
+)
+
+
+class SplitPdf(object):
+    def make_dir(self, newDir):
+        print("newDir in module", newDir)
+        self.directory = newDir
+        self.parent_dir = "../Documents/Converted/"
+        self.path = os.path.join(self.parent_dir, self.directory)
+        os.mkdir(self.path)
+
+    def split_and_convert(self, pathArg, newDir):
+        print("in split and convert: pathArg, newDir", pathArg, newDir)
+        arr = [
+            "a",
+            "b",
+            "c",
+            "d",
+            "e",
+            "f",
+            "g",
+            "h",
+            "i",
+            "j",
+            "k",
+            "l",
+            "m",
+            "n",
+            "o",
+            "p",
+            "q",
+            "r",
+            "s",
+            "t",
+            "u",
+            "v",
+            "w",
+            "x",
+            "y",
+            "z",
+            "aa",
+            "ab",
+            "ac",
+            "ad",
+            "ae",
+            "af",
+            "ag",
+            "ah",
+            "ai",
+            "ak",
+            "al",
+            "am",
+            "an",
+            "ao",
+            "ap",
+            "aq",
+            "ar",
+            "as",
+            "at",
+            "au",
+            "av",
+            "aw",
+            "ax",
+            "ay",
+            "az",
+            "ba",
+            "bb",
+            "bc",
+            "bd",
+            "be",
+            "bf",
+            "bg",
+            "bh",
+            "bi",
+            "bk",
+            "bl",
+            "bm",
+            "bn",
+            "bo",
+            "bp",
+            "bq",
+            "br",
+            "bs",
+            "bt",
+            "bu",
+            "bv",
+            "bw",
+            "bx",
+            "by",
+            "bz",
+            "za",
+            "zb",
+            "zc",
+            "zd",
+            "ze",
+            "zf",
+            "zg",
+            "zh",
+            "zi",
+            "zj",
+            "zk",
+            "zl",
+            "zm",
+            "zn",
+            "zo",
+            "zp",
+            "zq",
+            "zr",
+            "zs",
+            "zt",
+            "zu",
+            "zv",
+            "zw",
+            "zx",
+            "zy",
+            "zz",
+        ]
+        self.images = convert_from_path(pathArg, fmt="png")
+        print(f"../Documents/Converted/{self.directory}")
+        for i, image in enumerate(self.images):
+            fname = f"{newDir}" + arr[i] + ".png"
+            image.save(f"../Documents/Converted/{self.directory}/{fname}", "PNG")
+
+
+# split pdf to multiple png files
+# https://pypi.org/project/pdf2image/
+# https://pythonforundergradengineers.com/pdf-to-multiple-images.html
+# convert to js(?):
+# https://www.npmjs.com/package/pdf2image

ax3Services/docConvertService/watcher.py

@@ -0,0 +1,41 @@
+import sys
+import time
+import logging
+from splitPdf import SplitPdf
+from watchdog.observers import Observer
+from pathlib import Path
+
+# from watchdog.events import LoggingEventHandler
+from watchdog.events import PatternMatchingEventHandler
+
+watch_dir = f"{Path(__file__).parents[1]}/Documents/Uploads"
+
+if __name__ == "__main__":
+    sp = SplitPdf()
+
+    def on_created(event):
+        print(f"Event: {event.src_path} was created.")
+        path = str(event.src_path).split("/")
+        print(">>>>>>>>>>>>>>>path", path[-1].split(".")[0])
+        newDir = path[-1].split(".")[0]
+        sp.make_dir(newDir)
+        sp.split_and_convert(event.src_path, newDir)
+
+    patterns = ["*"]
+    ignore_patterns = None
+    ignore_directories = False
+    case_sensitive = True
+    path = watch_dir
+    my_event_handler = PatternMatchingEventHandler(
+        patterns, ignore_patterns, ignore_directories, case_sensitive
+    )
+    my_event_handler.on_created = on_created
+    observer = Observer()
+    observer.schedule(my_event_handler, path, recursive=True)
+    observer.start()
+    try:
+        while True:
+            time.sleep(1)
+    finally:
+        observer.stop()
+        observer.join()