From 5c56c8c2faae8312ad994d30f0f87b4494042c07 Mon Sep 17 00:00:00 2001
From: Jeniamakarchik <eniamak@gmail.com>
Date: Fri, 10 Apr 2020 17:04:30 +0300
Subject: [PATCH] fix heading support

---
 Dockerfile  |  2 ++
 src/book.py | 27 +++++++++++++--------------
 2 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index 1f21b13..a8afd0e 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -13,5 +13,7 @@ COPY . /app/
 
 WORKDIR /app/
 VOLUME /app/logs
+# VOLUME /app/html
+# VOLUME /app/json
 
 CMD python /app/src/util/check_packs.py && python /app/src/util/check_dirs.py && python /app/src/consumer.py
diff --git a/src/book.py b/src/book.py
index 2a7d488..a003e20 100644
--- a/src/book.py
+++ b/src/book.py
@@ -28,7 +28,11 @@ class Book:
         "Trebuchet MS": "trebuchet ms,helvetica,sans-serif",
         "Verdana": "verdana,geneva,sans-serif"
     }
-    SUPPORTED_HEADERS = ["h1", "h2", "h3"]
+
+    SUPPPORTED_LEVELS = 3
+    SUPPORTED_HEADERS = {"h1", "h2", "h3"}
+    HEADERS_LEVELS = {"h1", "h2", "h3", "h4", "h5", "h6", "h7", "h8", "h9"}
+
 
     def __init__(self, book_id=0, access=None, file_path=None, output_path=None, main_logger=None):
         self.book_id = book_id
@@ -45,6 +49,9 @@ class Book:
         self.images = list()
         self.content_dict = dict()
 
+        assert self.SUPPPORTED_LEVELS == len(self.SUPPORTED_HEADERS), \
+            "Length of headers doesn't match allowd levels."
+
     def configure_file_logger(self, name, attr_name='logger', filename='logs/book_log.log', filemode='w+',
                               logging_level=logging.INFO, logging_format='%(asctime)s - %(message)s'):
         """
@@ -514,16 +521,16 @@ class Book:
         """
         Function to convert all lower level headings to p tags
         """
-        header_tags = self.body_tag.find_all(re.compile("^h[4-6]$"))
+        pattern = f'^h[{self.SUPPPORTED_LEVELS + 1}-9]$'
+        header_tags = self.body_tag.find_all(re.compile(pattern))
         for tag in header_tags:
             tag.name = 'p'
-            print(tag)
 
     def _process_headings(self):
         """
         Function to process tags <h>.
         """
-        header_tags = self.body_tag.find_all(re.compile("^h[1-6]$"))
+        header_tags = self.body_tag.find_all(re.compile("^h[1-9]$"))
         for tag in header_tags:
             if tag.parent.name == "li":
                 tag.parent.unwrap()
@@ -535,18 +542,14 @@ class Book:
             if title == "":
                 tag.unwrap()
             else:
-                assert tag.name not in ["h4", "h5", "h6"], 'Preprocessing went wrong, there is still h4-h6 headings.'
+                assert tag.name in self.SUPPORTED_HEADERS, \
+                    f'Preprocessing went wrong, there is still h{self.SUPPPORTED_LEVELS+1}-h9 headings.'
                 # if tag.name in ["h4", "h5", "h6"]:
                 #     tag.name = "h3" # All the lower level headings will be transformed to h3 headings
 
 
                 new_tag = BeautifulSoup(features='lxml').new_tag(name=tag.name)
                 new_tag.string = title
-                if new_tag.name == "p":
-                    new_tag.attrs = tag.attrs
-                    print(tag)
-                    print(new_tag)
-
                 tag.replace_with(new_tag)
 
     def write_html_from_list(self, file_name='url_test.html'):
@@ -711,10 +714,6 @@ class Book:
             with codecs.open(self.output_path, 'w', encoding='utf-8') as f:
                 json.dump(self.content_dict, f, ensure_ascii=False)
             self.log('Data has been saved to .json file.')
-
-            from pprint import pprint
-
-            pprint(self.content_dict)
         except Exception as exc:
             self.log('Error has occurred while writing json file.', logging.ERROR)
             # self.log_error_to_main_log()