From dedac951d7ac097105402f6f89e1193cda0e3e64 Mon Sep 17 00:00:00 2001
From: felixwelter <felixwelter@gmail.com>
Date: Fri, 4 Sep 2020 15:57:05 +0200
Subject: [PATCH] Refactor; extract indexing routine into indexer class
---
app.py | 15 ++++++---------
slide_indexer/__init__.py | 1 +
slide_indexer/basic_indexer.py | 20 ++++++++++++++++++++
3 files changed, 27 insertions(+), 9 deletions(-)
create mode 100644 slide_indexer/__init__.py
create mode 100644 slide_indexer/basic_indexer.py
diff --git a/app.py b/app.py
index 1d890ef..8b52001 100644
--- a/app.py
+++ b/app.py
@@ -7,6 +7,7 @@ from flask import Flask, render_template, request, redirect, send_file, jsonify
from werkzeug.utils import secure_filename
from search_index import TitleFocusSearchIndex
+from slide_indexer import BasicIndexer
app = Flask(__name__)
@@ -32,6 +33,8 @@ def allowed_file(filename):
def upload():
if 'files' in request.files:
files = request.files.getlist('files')
+ index = Index(index_dir=INDEX_DIR)
+ indexer = BasicIndexer(index, IMAGE_DIR)
for i, file in enumerate(files):
print(i, file)
if file.filename != '':
@@ -39,15 +42,9 @@ def upload():
filename = secure_filename(file.filename)
file_path = os.path.join(Path(SLIDE_DIR), filename)
file.save(file_path)
- pdf = pdfplumber.open(file_path)
- index = Index(index_dir=INDEX_DIR)
- for i, page in enumerate(pdf.pages):
- text = page.extract_text()
- index.add(str(file_path), i, text, text.split("\n")[0]) # Assumes title in the first line
- img_name = str(file_path)[7:] + "_" + str(i) + ".jpg"
- img_path = os.path.join(IMAGE_DIR, img_name)
- page.to_image().save(img_path)
- del index
+ indexer.add_pdf(file_path)
+ del indexer
+ del index
return redirect('/')
diff --git a/slide_indexer/__init__.py b/slide_indexer/__init__.py
new file mode 100644
index 0000000..6c58274
--- /dev/null
+++ b/slide_indexer/__init__.py
@@ -0,0 +1 @@
+from .basic_indexer import BasicIndexer
\ No newline at end of file
diff --git a/slide_indexer/basic_indexer.py b/slide_indexer/basic_indexer.py
new file mode 100644
index 0000000..fbb3201
--- /dev/null
+++ b/slide_indexer/basic_indexer.py
@@ -0,0 +1,20 @@
+import os
+
+import pdfplumber
+
+
+class BasicIndexer():
+ def __init__(self, index, image_dir):
+ self.index = index
+ self.image_dir = image_dir
+
+ def add_pdf(self, file_path):
+ pdf = pdfplumber.open(file_path)
+ for i, page in enumerate(pdf.pages):
+ text = page.extract_text()
+ self.index.add(str(file_path), i, text, text.split("\n")[0]) # Assumes title in the first line
+ img_name = str(file_path)[7:] + "_" + str(i) + ".jpg"
+ img_path = os.path.join(self.image_dir, img_name)
+ page.to_image().save(img_path)
+
+
--
GitLab