feat: Removed docx and added PDF support

.dockerignore

@@ -0,0 +1,3 @@
+__pycache__/
+Dockerfile
+templated-image.tar.gz

.gitignore

@@ -104,3 +104,4 @@ venv.bak/
 
 # End of https://www.gitignore.io/api/python
 .idea/
+templated-image.tar.gz

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3
+
+WORKDIR /usr/src/app
+
+RUN apt-get -qq update && \
+    apt-get -q -y upgrade && \
+    apt-get install -y locales && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN sed -i -e 's/# en_US.UTF-8 UTF-8/en_US.UTF-8 UTF-8/' /etc/locale.gen && \
+    sed -i -e 's/# nl_NL.UTF-8 UTF-8/nl_NL.UTF-8 UTF-8/' /etc/locale.gen && \
+    locale-gen
+
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 1212
+
+CMD ["python", "./test.py"]

docx_replacement.py

@@ -1,22 +0,0 @@
-from docx import Document
-from xlsx_replacement import XlsxReplacement
-
-
-def docx_replace_regex(doc_obj: Document, replacer: XlsxReplacement):
-    for p in doc_obj.paragraphs:
-        if '[[' in p.text:
-            inline = p.runs
-            # Loop added to work with runs (strings with same style)
-            for i in range(len(inline)):
-                if '[[' in inline[i].text:
-                    text = replacer.find_replace_text(inline[i].text)
-                    inline[i].text = text
-
-    for table in doc_obj.tables:
-        for row in table.rows:
-            for cell in row.cells:
-                docx_replace_regex(cell, replacer)
-
-
-def load_document(file):
-    return Document(file)

pdf_merger.py

@@ -0,0 +1,42 @@
+from PyPDF2 import PdfFileReader, PdfFileWriter
+import io
+from reportlab.pdfgen import canvas
+from reportlab.lib.pagesizes import A4
+from typing import IO, Union
+
+from xlsx_replacement import XlsxReplacement
+
+
+class PdfMerger:
+    def __init__(self, input_file: Union[str, IO], replacer: XlsxReplacement):
+        self.in_file = input_file
+        self.in_pdf = PdfFileReader(input_file)
+        self.replacer = replacer
+
+    def get_new_document(self) -> io.BytesIO:
+        overlay = PdfFileReader(self._build_canvas())
+
+        generated = PdfFileWriter()
+
+        for i in range(self.in_pdf.numPages):
+            page = self.in_pdf.getPage(i)
+            if i <= overlay.numPages:
+                page.mergePage(overlay.getPage(i))
+            generated.addPage(page)
+
+        out = io.BytesIO()
+        generated.write(out)
+        out.seek(0)
+        return out
+
+    def _build_canvas(self) -> io.BytesIO:
+        packet = io.BytesIO()
+
+        can = canvas.Canvas(packet, pagesize=A4)
+        for x, y, data in self.replacer.get_replacements():
+            can.drawString(x, y, data)
+        can.save()
+
+        packet.seek(0)
+        return packet
+    pass

requirements.txt

@@ -0,0 +1,4 @@
+PyPDF2
+openpyxl
+reportlab
+Flask

test.py

@@ -1,41 +1,32 @@
 #!/usr/bin/env python3
-from flask_api import FlaskAPI
 from flask import Flask, request, send_file
-from docx_replacement import docx_replace_regex, load_document
 from xlsx_replacement import XlsxReplacement
-from io import BytesIO
+from pdf_merger import PdfMerger
 
-# app = FlaskAPI(__name__)
 app = Flask(__name__)
 
 
-@app.route('/docx-test/docx_replace', methods=['POST'])
+@app.route('/pdf-test/pdf_replace', methods=['POST'])
 def test_upload():
     if request.files is None or len(request.files) == 0:
         raise ValueError("Files required!")
 
-    if 'xlsx' not in request.files or 'docx' not in request.files:
+    if 'xlsx' not in request.files or 'pdf' not in request.files:
         raise ValueError('Missing xlsx or docx')
 
     xlsx = XlsxReplacement(request.files['xlsx'])
-    docx = load_document(request.files['docx'])
+    merger = PdfMerger(request.files['pdf'], xlsx)
-
+    out = merger.get_new_document()
-    docx_replace_regex(docx, xlsx)
+    return send_file(out, mimetype='application/pdf', attachment_filename=request.files['pdf'].filename)
-
-    bio = BytesIO()
-    docx.save(bio)
-    bio.seek(0)
-    return send_file(bio, mimetype='application/vnd.openxmlformats-officedocument.wordprocessingml.document',
-                     attachment_filename=request.files['docx'].filename)
 
 
-@app.route('/docx-test/testpage')
+@app.route('/pdf-test/testpage')
 def test_page():
     return """
     <html><body>
-    <form action="/docx-test/docx_replace" method="post" enctype="multipart/form-data">
+    <form action="/pdf-test/pdf_replace" method="post" enctype="multipart/form-data">
-    <label>Select DOCX
+    <label>Select PDF
-    <input type="file" name="docx" id="docx"></label>
+    <input type="file" name="pdf" id="pdf"></label>
     <label>Select XLSX
     <input type="file" name="xlsx" id="xlsx"></label>
     <input type="submit" value="Upload" name="submit">

xlsx_replacement.py

@@ -1,34 +1,50 @@
 import re
 import openpyxl
-from typing import Union, IO
+from openpyxl.cell import Cell
+from typing import Union, Tuple, Iterator, IO
+import locale
 
 
 class XlsxReplacement:
     def __init__(self, file: Union[str, IO]):
         self.file = file
         self.xlsx = openpyxl.load_workbook(file, read_only=True, data_only=True)
-        self.re_replace = re.compile('\[\[(?:(\w+):)?([a-zA-Z]+\d+)\]\]')
         self.errors = []
+        self.reset_settings = {}
 
-    def find_replace_text(self, text: str):
+    def get_replacements(self) -> Iterator[Tuple[int, int, str]]:
-        if '[[' not in text:
+        self._get_settings()
-            return text
+        sheet = self.xlsx['replacements']
+        for row in sheet.iter_rows(min_row=1, max_col=5):
+            content = [c.value for c in row]
+            x = int(content[0])
+            y = int(content[1])
+            value = content[2]
+            if len(content) == 5:
+                value_format = content[3]
+                str_format = content[4]
+                print(value_format)
+                print(str_format)
+                if value_format is not None and isinstance(value_format, str) and len(value_format) > 0:
+                    value = locale.format(value_format, value)
+                if str_format is not None and isinstance(str_format, str) and len(str_format) > 0:
+                    value = str_format.format(value)
+            if not isinstance(value, str):
+                value = str(value)
+            yield x, y, value
 
-        return self.re_replace.sub(self._regex_replacement, text)
+    def _get_settings(self):
+        sheet = self.xlsx['settings']
+        for row in sheet.iter_rows(max_col=2):
+            key, value = [i.value for i in row]
+            if key == 'locale':
+                print("Using locale %s" % value)
+                old_locale = '.'.join(locale.getlocale())
+                locale.setlocale(locale.LC_ALL, value)
+                self.reset_settings['locale'] = old_locale
 
-    def _regex_replacement(self, match):
+    def _reset_settings(self):
-        sheet, cell = match.groups()
+        for key, value in self.reset_settings:
-        if sheet is None:
+            if key == 'locale':
-            sheet = self.xlsx.active
+                locale.setlocale(locale.LC_ALL, value)
-        else:
-            try:
-                sheet = self.xlsx[sheet]
-            except IndexError:
-                self.errors.append('Unknown sheet {sheet}'.format(sheet=sheet))
-                return 'ERR Unknown sheet'
-        try:
-            return str(sheet[cell].value)
-        except (IndexError, ValueError):
-            self.errors.append('Unknown cell {sheet}:{cell}'.format(sheet=sheet, cell=cell))
-            return 'ERR Unknown cell'