ホーム エクスプローラ ヘルプ
サインイン
bscheibel
/
ui
Watch 1
Star 0
Fork 0
ファイル 課題 0 プルリクエスト 0 Wiki
ソースを参照

showing isos works, working on linking them

bscheibel 4 年 前
親
752ccc990e
コミット
2a37160dea
共有4 個のファイルを変更した、129 個の追加 と 10 個の削除を含む
分割表示 差分情報を表示
  1. 5 2
      app/static/css/style.css
  2. 10 1
      app/templates/show_image.html
  3. 15 7
      app/views.py
  4. 99 0
      order_bounding_boxes_in_each_block.py

+ 5 - 2
app/static/css/style.css
ファイルの表示 

@@ -54,9 +54,12 @@ body {
 
   text-align: center;
 
   margin: 10;
 
 }
 
-
 
+.thick-border {
 
+        border: 3px solid black;
 
+        border-collapse: collapse;
 
+}
 
 /* Style the image inside the centered container, if needed */
 
 .centered img {
 
   max-width: 140%;
 
   /*border-radius: 50%;
 
-}
 
+}

+ 10 - 1
app/templates/show_image.html
ファイルの表示 

@@ -23,7 +23,7 @@
 
   <div class="top">
 
     <div style="text-indent:50px;">
 
       <h1>Extracted Tolerances</h1>
 
-      <p>Maße: </p>
 
+      <p>Maße: {{ dims }} </p>
 
       <p><a href="http://localhost:5000/"> Upload another drawing </a></p>
 
     </div>
 
   </div>
 
@@ -32,6 +32,15 @@
 
   <div class="bottom">
 
     <div style="text-indent:50px;">
 
       <h1>Additional Requirements:</h1>
 
+      <table>
 
+
 
+        {% for k in isos %}
 
+                <tr>
 
+                        <td><a href="path/doc.pdf">My Resume</a> {{ k }}</td>
 
+                </tr>
 
+        {% endfor %}
 
+      </table>
 
+
 
     </div>
 
     </div>
 
 </div>

+ 15 - 7
app/views.py
ファイルの表示 

@@ -3,7 +3,10 @@ import os
 
 from flask import make_response
 
 from flask import Flask, request, redirect, url_for, send_from_directory, render_template
 
 import subprocess
 
-import time
 
+import order_bounding_boxes_in_each_block
 
+import redis
 
+import random
 
+import json
 
 #https://medium.com/@emerico/convert-pdf-to-image-using-python-flask-2864fb655e01
 
 
 
@@ -27,7 +30,9 @@ def upload_file():
 
             #image = wandImage(filename=filename)
 
             #image.save(os.path).join(app.config["UPLOAD_FOLDER"], filename)
 
             file.save(os.path.join(app.config["UPLOAD_FOLDER"], filename))
 
-            return redirect(url_for('uploaded_file', filename=filename))
 
+            uuid = random.randint(100,10000000)
 
+            order_bounding_boxes_in_each_block.main(uuid, UPLOAD_FOLDER+"/"+filename)
 
+            return redirect(url_for('uploaded_file', filename=filename, uuid=uuid))
 
     return '''
 
     <!doctype html>
 
     <title>Upload new File</title>
 
@@ -42,13 +47,15 @@ def convert_pdf(filename):
 
     subprocess.call(['pdftoppm', '-jpeg', '-singlefile',
 
                      PDFFILE, '/home/bscheibel/uploads_app/out'])
 
 
-@app.route('/show/<filename>')
 
-
 
-def uploaded_file(filename):
 
+@app.route('/show/<filename>&<uuid>')
 
+def uploaded_file(filename, uuid):
 
     file_out = "out.jpg"
 
     if filename.endswith(".pdf") or filename.endswith(".PDF"):
 
         convert_pdf(filename)
 
-        return render_template('show_image.html', filename=file_out)
 
+        db = redis.Redis("localhost")
 
+        #uuid = "dd"
 
+        isos = json.loads(db.get(uuid))
 
+        return render_template('show_image.html', filename=file_out, isos=isos)
 
 
     else:
 
         filename = filename
 
@@ -65,4 +72,5 @@ def add_header(response):
 
     response.headers['Cache-Control'] = 'no-store, no-cache, must-revalidate, post-check=0, pre-check=0, max-age=0'
 
     response.headers['Pragma'] = 'no-cache'
 
     response.headers['Expires'] = '-1'
 
-    return response
 
+    return response
 
+

+ 99 - 0
order_bounding_boxes_in_each_block.py
ファイルの表示 

@@ -0,0 +1,99 @@
 
+### FIRST READ EACH BLOCK IN AN ARRAY
 
+
 
+from bs4 import BeautifulSoup
 
+import subprocess
 
+import redis
 
+import re
 
+import json
 
+
 
+def get_bound_box(uuid, file):
 
+    print(file)
 
+    response = open(file)
 
+    html_doc = response.read()
 
+    response.close()
 
+    html_file = BeautifulSoup(html_doc, 'html.parser')
 
+
 
+    all_elements = []
 
+    blocks = html_file.findAll('block')
 
+    for block in blocks:
 
+        list_elements = []
 
+        words = block.findAll('word')
 
+        for word in words:
 
+            word_list = []
 
+            word_list.append(word["xmin"])
 
+            word_list.append(word["ymin"])
 
+            word_list.append(word["xmax"])
 
+            word_list.append(word["ymax"])
 
+            word_list.append(word.string)
 
+            list_elements.append(word_list)
 
+        all_elements.append(list_elements)
 
+
 
+
 
+    #### NEXT SORT ELEMENTS IN EACH BLOCK BY THEIR X AND Y COORDINATES
 
+    #### FIRST TRYING XMIN und YMAX
 
+    ###FIRST CHECKING IF THE ELEMENTS ARE VERTICAL, IF YES THEN NO SORTING
 
+    new_all_elements = []
 
+
 
+    for element in all_elements:
 
+        later_bigger = (float(element[-1][0])-(float(element[0][0]))) #check if xmin from first element is bigger than xmin from last element
 
+        abstand_x = abs(float(element[-1][0])-(float(element[0][2])))
 
+        abstand_y = abs(float(element[-1][3])-float(element[0][1]))
 
+        if later_bigger >= -5:
 
+            #print(abstand_x-abstand_y)
 
+            new_all_elements.append(element)
 
+        else:
 
+            new_element = sorted(element, key=lambda k: [float(k[0])])
 
+            new_all_elements.append(new_element)
 
+
 
+
 
+    """for element in new_all_elements:
 
+        for blub in element:
 
+            #print(blub[4])
 
+
 
+        #print("\n")"""
 
+
 
+
 
+    db = redis.Redis("localhost")
 
+    db.set(uuid, "test")
 
+    return new_all_elements, uuid
 
+
 
+def pdf_to_html(uuid,filepath):
 
+    subprocess.call(['pdftotext', '-bbox-layout',
 
+                     filepath, str(uuid)+'out.html'])
 
+
 
+def extract_isos(result):
 
+    reg = r"(ISO\s\d\d\d\d*\W?\d?\W?\d?)|(EN\s\d*)"
 
+    details_ = []
 
+    for element in result:
 
+        new_arr = ""
 
+        #print(element)
 
+        for x in element:
 
+            new_arr += x[4] + " "
 
+        print(new_arr)
 
+        if re.search(reg,new_arr):
 
+            #print(new_arr)
 
+            found = re.findall(reg, new_arr)
 
+            for f in found:
 
+                if len(f[0]) != 0:
 
+                    details_.append(f[0].replace(")",""))
 
+                if len(f[1]) != 0:
 
+                    details_.append(f[1])
 
+    return details_
 
+
 
+def main(uuid, result):
 
+    pdf_to_html(uuid, result)
 
+    res, uuid = get_bound_box(uuid, str(uuid)+"out.html")
 
+    isos = extract_isos(res)
 
+    isos_j = json.dumps(isos)
 
+    db = redis.Redis("localhost")
 
+    print(isos)
 
+    db.set(uuid, str(isos_j))
 
+
 
+"""file = "/home/bscheibel/PycharmProjects/dxf_reader/drawings/5129275_Rev01-GV12.html"
 
+res, uuid = get_bound_box("uuu", file)
 
+isos = extract_isos(res)
 
+print(isos)
 
+#pdf_to_html("/home/bscheibel/PycharmProjects/dxf_reader/drawings/5129275_Rev01-GV12.pdf")
 
+"""
 
+
 
+#main("uud","/home/bscheibel/PycharmProjects/dxf_reader/drawings/5129275_Rev01-GV12.pdf")