444 verify git link

app/main/check_packs/pack_config.py

@@ -16,6 +16,8 @@
     ['future_dev'],
     ['pres_banned_words_check'],
     ['pres_empty_slide'],
+    ['pres_banned_words_check'],
+    ['verify_git_link'],
 ]
 BASE_REPORT_CRITERION = [
     ["simple_check"],

app/main/checks/__init__.py

@@ -15,6 +15,7 @@
         PresImageShareCheck.id: PresImageShareCheck,
         FurtherDev.id: FurtherDev,
         PresBannedWordsCheck.id: PresBannedWordsCheck,
+        PresVerifyGitLinkCheck.id: PresVerifyGitLinkCheck,
         PresEmptySlideCheck.id: PresEmptySlideCheck,
     },
     'report': {

app/main/checks/presentation_checks/__init__.py

@@ -10,4 +10,5 @@
 from .pres_right_words import PresRightWordsCheck
 from .image_share import PresImageShareCheck
 from .banned_words import PresBannedWordsCheck
+from .verify_git_link import PresVerifyGitLinkCheck
 from .empty_slide_check import PresEmptySlideCheck

app/main/checks/presentation_checks/find_def_sld.py

@@ -8,18 +8,21 @@ class FindDefSld(BasePresCriterion):
     def __init__(self, file_info, key_slide):
         super().__init__(file_info)
         self.type_of_slide = key_slide
+        self.found_idxs = []
 
     def check(self):
-        found_slides, found_idxs = [], []
+        found_slides = []
         for i, title in enumerate(self.file.get_titles(), 1):
             if str(title).lower().find(str(self.type_of_slide).lower()) != -1:
                 found_slides.append(self.file.get_text_from_slides()[i - 1])
-                found_idxs.append(i)
+                self.found_idxs.append(i)
         if len(found_slides) == 0:
+            self.file.found_index[str(self.type_of_slide)] = None
             return answer(False, 'Слайд не найден')
         else:
-            found_idxs = self.format_page_link(found_idxs)
-            return answer(True, 'Найден под номером: {}'.format(', '.join(map(str, found_idxs))))
+            self.file.found_index[str(self.type_of_slide)] = ''.join(str(item) for item in self.found_idxs)
+            found_idxs_link = self.format_page_link(self.found_idxs)
+            return answer(True, 'Найден под номером: {}'.format(', '.join(map(str, found_idxs_link))))
 
     @property
     def name(self):

app/main/checks/presentation_checks/verify_git_link.py

@@ -0,0 +1,89 @@
+
+import re
+import requests
+from lxml import html
+from urllib.parse import quote
+
+from .find_def_sld import FindDefSld
+from ..base_check import BasePresCriterion, answer
+
+#  for check if gitlab-repository is closed:
+# GITLAB_URL = 'https://gitlab.com/api/v4'
+# PRIVATE_TOKEN = 'glpat-JeZApxShRgB1nsGrMsst'
+
+
+class PresVerifyGitLinkCheck(BasePresCriterion):
+    description = "Проверка действительности ссылки на github"
+    id = 'verify_git_link'
+
+    def __init__(self, file_info, deep_check=True):
+        super().__init__(file_info)
+        self.deep_check = deep_check
+        self.wrong_repo_ref = []
+        self.empty_repo_ref = []
+
+        # self.check_aprb = FindDefSld(file_info=file_info, key_slide="Апробация")
+        self.pattern_for_repo = r'((((((http(s)?://)?(github|gitlab|bitbucket)+)+(.com|.org)+)+/[a-zA-Z0-9_-]+)+/[a-zA-Z0-9_-]+)+/*)+'
+        self.pattern_for_repo_incorrect = r'\(github\.com\)|\(gitlab\.com\)|\(bitbucket\.org\)|\(github\)|\(gitlab\)|\(bitbucket\)'
+        self.pattern_repo_mention = r'репозиторий|репозитория|репозиторию|репозиториев|репозиториям|'
+
+    def check(self):
+        string_result = 'Не пройдена!'
+        text_from_slide = [slide for page, slide in enumerate(self.file.get_text_from_slides(), 1)]
+        string_from_text = ' '.join(text_from_slide)
+        found_repo = re.findall(self.pattern_for_repo, string_from_text)
+
+        if not found_repo:
+            return answer(True, 'Нечего проверять!')
+
+        else:
+            if self.file.found_index['Апробация'] is not None:
+                page_aprb = self.file.found_index['Апробация']
+                text_from_slide_aprb = [
+                    slide.replace(" ", '') for page, slide in enumerate(self.file.get_text_from_slides(), 1)
+                    if str(page) == page_aprb]
+
+                string_from_text_aprb = ' '.join(text_from_slide_aprb)
+                found_repo_aprb = re.findall(self.pattern_for_repo, string_from_text_aprb)
+                found_repo_aprb_incorrect = re.findall(self.pattern_for_repo_incorrect, string_from_text_aprb)
+                if found_repo_aprb_incorrect:
+                    string_result += f" <br> В слайде 'Апробация' вместо выражений {', '.join([repr(repo) for repo in found_repo_aprb_incorrect])}" \
+                                     f" следует привести ссылки вида 'https//github.com/...'"
+                if not found_repo_aprb and not found_repo_aprb_incorrect and re.findall(self.pattern_repo_mention, string_from_text_aprb):
+                    string_result += f' <br> В слайде "Апробация" есть упоминания репозиториев,' \
+                                     f'однако ссылки на них либо некорректны, либо отсутствуют.'
+
+            for i in found_repo:
+                try:
+                    link = requests.get(i[0])
+                    if link.status_code != 200:
+                        raise requests.exceptions.ConnectionError
+                    else:
+                        if self.deep_check:
+                            self.deep_check_repo(i, link)
+                except (requests.exceptions.SSLError, requests.exceptions.ConnectionError):
+                    self.wrong_repo_ref.append(i[0])
+        if self.wrong_repo_ref:
+            string_result += f" <br> Найдены несуществующие или закрытые репозитории: {', '.join([repr(repo) for repo in self.wrong_repo_ref])}"
+            check_result = False
+        if self.empty_repo_ref:
+            string_result += f" <br> Найдены пустые репозитории: {', '.join([repr(repo) for repo in self.empty_repo_ref])}"
+            check_result = False
+        else:
+            string_result = 'Пройдена!'
+            check_result = True
+        return answer(check_result, string_result)
+
+    def deep_check_repo(self, repo, link):
+        if re.findall(r'github', repo[0]):
+            tree = html.fromstring(link.content)
+            if not tree.xpath("//a[@class ='js-navigation-open Link--primary']"):
+                self.empty_repo_ref.append(repo[0])
+
+        # if re.findall(r'gitlab', i[0]):
+        #     project_id = quote(i[0].replace('https://gitlab.com/', ''), safe='')
+        #     url = f'{GITLAB_URL}/projects/{project_id}?private_token={PRIVATE_TOKEN}'
+        #     response = requests.get(url)
+        #     project_info = response.json()
+        #     if project_info['visibility'] == 'private':
+        #         wrong_repo_ref.append(i[0])

app/main/presentations/pptx/presentation_pptx.py

@@ -9,6 +9,7 @@ def __init__(self, presentation_name):
         PresentationBasic.__init__(self, presentation_name)
         self.prs = Presentation(presentation_name)
         self.add_slides()
+        self.found_index = {}
 
     def add_slides(self):
         for index, slide in enumerate(self.prs.slides, 1):

app/server.py

@@ -275,6 +275,7 @@ def get_status(task_id):
                    'pres_image_share': 'Проверка доли объема презентации, приходящейся на изображения',
                    'pres_banned_words_check': 'Проверка наличия запретных слов в презентации',
                    'conclusion_actual': 'Соответствие заключения задачам',
+                   'verify_git_link': 'Проверка действительности ссылки на github',
                    'conclusion_along': 'Наличие направлений дальнейшего развития',
                    'simple_check': 'Простейшая проверка отчёта',
                    'banned_words_in_literature': 'Наличие запрещенных слов в списке литературы',

requirements.txt

@@ -1,7 +1,7 @@
 werkzeug==2.0.0
 Flask==2.0.3
 jinja2==3.0.0
-requests==2.24.0
+requests~=2.31.0
 python-pptx==0.6.18
 odfpy==1.4.1
 pymongo==3.11.1
@@ -25,6 +25,8 @@ docx2python~=2.0.4
 oauthlib~=3.1.0
 pdfplumber==0.6.1
 pytest~=7.1.2
+lxml~=4.9.2
+urllib3~=2.0.3
 filetype==1.2.0
 language-tool-python==2.7.1
 markdown==3.4.4