Refactor to use Cython properties

Author: jdcaballerov

pyzim/examples.py

@@ -7,7 +7,7 @@
 <h1> Hola Funciona </h1></html>'''
 
 
-article = pyzim.ZimArticle(ns='A', url = 'Monadical', title='Monadical SAS', content=content.encode(), should_index = True)
+article = pyzim.ZimArticle(namespace='A', url = 'Monadical', title='Monadical SAS', content=content, should_index = True)
 
 import uuid
 
@@ -17,6 +17,7 @@
 
 zim_creator = pyzim.ZimCreator(test_zim_file_path + '-' + rnd_str + '.zim',"welcome","eng",2048)
 zim_creator.add_article(article)
+zim_creator.finalise()
 
 test_zim_reader = pyzim.ZimReader(test_zim_file_path + '-' + rnd_str + '.zim')
 

pyzim/pyzim.pyx

@@ -1,5 +1,4 @@
 from libcpp.string cimport string
-from libc.stdint cimport uint32_t, uint64_t
 from libcpp cimport bool
 from libcpp.memory cimport shared_ptr, make_shared
 
@@ -24,25 +23,28 @@ cdef class ZimArticle:
     ----------
     *c_zim_article : zim.ZimArticle
         a pointer to the C++ article object
-    _namespace : str
+    _can_write : bool
+        flag if the article is ready for writing
+
+    Properties
+    -----------
+    namespace: str
         the article namespace
-    _title : str
+    title : str
         the article title
-    _content : str
+    content : str
         the article content
-    _longurl : str
+    longurl : str
         the article long url i.e {NAMESPACE}/{redirect_url}
-    _url : str
+    url : str
         the article url
-    _mimetype : str
+    mimetype : str
         the article mimetype
-    _is_redirect : bool
+    is_redirect : bool
         flag if the article is a redirect 
-    _can_write : bool
-        flag if the article is ready for writing
-    _redirect_longurl: str
+    redirect_longurl: str
         the long redirect url i.e {NAMESPACE}/{redirect_url}
-    _redirect_url : str
+    redirect_url : str
         the article url
 
     Methods
@@ -53,40 +55,27 @@ cdef class ZimArticle:
 
     """
     cdef zim.ZimArticle *c_zim_article
-    cdef object _namespace
-    cdef object _title
-    cdef object _content
-    cdef object _longurl
-    cdef object _url
-    cdef object _mimetype
-    cdef object _is_redirect
     cdef object _can_write
-    cdef object _redirect_longurl
-    cdef object _redirect_url
 
     VALID_NAMESPACES = ["-","A","B","I","J","M","U","V","W","X"]
 
 
-    def __cinit__(self, url="", str content="", namespace= "A", mimetype= "text/html", title="", redirect_article_url= "", article_id = "",filename="", should_index=True ):
+    def __cinit__(self, url="", str content="", namespace= "A", mimetype= "text/html", title="", redirect_article_url= "",filename="", should_index=True ):
 
         # Encoding must be set to UTF-8 
-        cdef bytes py_bytes = content.encode(encoding='UTF-8')
-        cdef char* c_string = py_bytes
+        #cdef bytes py_bytes = content.encode(encoding='UTF-8')
+        #cdef char* c_string = py_bytes
 
         if namespace not in self.VALID_NAMESPACES:
             raise RuntimeError("Invalid Namespace")
 
         c_zim_art = new zim.ZimArticle(ord(namespace),                     # Namespace
-                                       article_id.encode('UTF-8'),         # Article index
                                        url.encode('UTF-8'),                # url
                                        title.encode('UTF-8'),              # title
                                        mimetype.encode('UTF-8'),           # mimeType
                                        redirect_article_url.encode('UTF-8'),# redirectUrl
-                                       filename.encode('UTF-8'),           # filename
-                                       True,                       # shouldIndex
-                                       c_string,                           # data buffer
-                                       len(c_string))                      # data buffer length   
-    
+                                       should_index,                                # shouldIndex
+                                       content.encode('UTF-8'))
         self.__setup(c_zim_art)
 
     def __dealloc__(self):
@@ -104,95 +93,31 @@ cdef class ZimArticle:
         A python ZimArticle always maintains a pointer to a wrapped zim.ZimArticle C++ object. 
         The python object reflects the state, accessible with properties, of a wrapped C++ zim.ZimArticle,
         this ensures a valid wrapped article that can be passed to a zim.ZimCreator.
-        
 
         Parameters
         ----------
         *art : zim.ZimArticle
             Pointer to a C++ article object
 
         """
-
-        # Delete old internal C zim.ZimArticle article if any
-        if self.c_zim_article != NULL:
-            del self.c_zim_article
-
         # Set new internal C zim.ZimArticle article
         self.c_zim_article = art
 
-        # Setup members
-        self._title = self.c_zim_article.getTitle().decode("UTF-8", "strict") 
-
-        b = self.c_zim_article.getData()
-        #print("******************     B.DATA() de %s ***********************" % self._title)
-        #print(b.data())
-        self._content = b.data()[:b.size()].decode("UTF-8", "strict")
-
-        self._longurl = self.c_zim_article.getUrl().getLongUrl().decode("UTF-8", "strict") 
-        self._url = self._longurl[2:]        
-        self._namespace = self._longurl[0]
-
-        self._redirect_longurl = self.c_zim_article.getRedirectUrl().getLongUrl().decode("UTF-8", "strict")
-        self._redirect_url = self._redirect_longurl[2:]  
-
-        self._mimetype = self.c_zim_article.getMimeType().decode("UTF-8", "strict")
-        self._is_redirect = self.c_zim_article.isRedirect()
-        
         # An article must have at least non empty url to be writable
         # Content can be empty if article is a redirect
-        if self._longurl.strip() and (self._content.strip() or self._is_redirect):
+        if self.longurl and (self.content or self.is_redirect):
             self._can_write = True
         else:
             self._can_write = False
 
     def get_article_properties(self):
         return dict((name, getattr(self, name)) for name in dir(self) if not name.startswith('__') )
 
-    # props is a dictionary, Cython cdef can't use **kwargs
-    cdef update_c_zim_article_from_properties(self, dict props):
-
-        # Encoding must be set to UTF-8 
-        cdef bytes py_bytes = props.get("content",u"").encode()
-        cdef char* c_string = py_bytes
-
-        ns = ord(props["namespace"])
-        article_id = props.get("article_id","")
-        url = props["url"]
-        title = props["title"]
-        mimetype = props["mimetype"]
-        redirect_article_url = props.get("redirect_url")
-        filename = props.get("filename","")
-        should_index = props.get("should_index",True)
-
-
-        c_zim_art = new zim.ZimArticle(ns,                                 # Namespace
-                                       "".encode('UTF-8'),                 # Article index
-                                       url.encode('UTF-8'),                # url
-                                       title.encode('UTF-8'),              # title
-                                       mimetype.encode('UTF-8'),           # mimeType
-                                       redirect_article_url.encode('UTF-8'),# redirectAid
-                                       "".encode('UTF-8'),                  # filename
-                                       should_index,                       # shouldIndex
-                                       c_string,                           # data buffer
-                                       len(c_string))                      # data buffer lengt  
-        
-
-        self.__setup(c_zim_art) 
-
-    def _update_property(self, **kwargs):
-        properties = self.get_article_properties()
-        properties.update(kwargs)
-
-        self.update_c_zim_article_from_properties(properties)
-
     # Factory functions - Currently Cython can't use classmethods
     @staticmethod
     cdef from_read_article(zim.Article art):
         """Creates a python ZimArticle from a C++ zim.Article article.
-
-        Retu
         
-
         Parameters
         ----------
         art : zim.ZimArticle
@@ -208,98 +133,89 @@ cdef class ZimArticle:
     @property
     def namespace(self):
         """Get the article's namespace"""
-        return self._namespace
+        return chr(self.c_zim_article.ns)
 
     @namespace.setter
     def namespace(self,new_namespace):
         """Set the article's namespace"""
-        self._update_property(namespace=new_namespace)
-
+        if new_namespace not in self.VALID_NAMESPACES:
+            raise RuntimeError("Invalid Namespace")
+        self.c_zim_article.ns = ord(new_namespace[0])
+        
     @property
     def title(self):
         """Get the article's title"""
-        return self._title
+        return self.c_zim_article.title.decode('UTF-8')
 
     @title.setter
     def title(self, new_title):
         """Set the article's namespace"""
-        self._update_property(title=new_title)
+        self.c_zim_article.title = new_title.encode('UTF-8')
 
     @property
     def content(self):
         """Get the article's content"""
-        return self._content
+        return self.c_zim_article.content.decode('UTF-8')
 
     @content.setter
     def content(self, new_content):
         """Set the article's content"""
-        self._update_property(content=new_content)
+        self.c_zim_article.content = new_content.encode('UTF-8') 
 
     @property
     def longurl(self):
         """Get the article's long url i.e {NAMESPACE}/{url}"""
-        return self._longurl
+        return self.c_zim_article.getUrl().getLongUrl().decode("UTF-8", "strict")
 
     @property
     def url(self):
         """Get the article's url"""
-        return self._url
+        return self.c_zim_article.url.decode('UTF-8')
 
     @url.setter
     def url(self, new_url):
         """Set the article's url"""
-        self._update_property(url=new_url)
+        self.c_zim_article.url = new_url.encode('UTF-8')
 
     @property
     def redirect_longurl(self):
         """Get the article's redirect long url i.e {NAMESPACE}/{redirect_url}"""
-        return self._redirect_longurl
+        return self.c_zim_article.getRedirectUrl().getLongUrl().decode("UTF-8", "strict")
 
     @property
     def redirect_url(self):
         """Get the article's redirect url"""
-        return self._redirect_url
+        return self.c_zim_article.redirectUrl.decode('UTF-8')
 
     @redirect_url.setter
     def redirect_url(self, new_redirect_url):
         """Set the article's redirect url"""
-        self._update_property(redirect_url=new_redirect_url)
+        self.c_zim_article.redirectUrl = new_redirect_url.encode('UTF-8')
 
     @property
     def mimetype(self):
         """Get the article's mimetype"""
-        return self._mimetype
+        return self.c_zim_article.mimeType.decode('UTF-8')
 
     @mimetype.setter
     def mimetype(self, new_mimetype):
         """Set the article's mimetype"""
-        self._update_property(mimetype=new_mimetype)
+        self.c_zim_article.mimeType = new_mimetype.encode('UTF-8')
 
     @property
     def is_redirect(self):
         """Get if the article is a redirect"""
-        return self._is_redirect
+        return self.c_zim_article.isRedirect()
 
     @property
     def can_write(self):
         """Get if the article is valid for writing"""
+        if self.longurl and (self.content or self.is_redirect):
+            self._can_write = True
+        else:
+            self._can_write = False
         return self._can_write
 
-    # ZimArticle.good only available for zim:Article
-    #def _good(self):
-    #    return self.c_zim_article.good()
-
-    # ZimArticle.getRedirectArticle only available for zim:Article
-    #def get_redirect_article(self):
-    #    cdef Article article = Article()
-    #    cdef zim.Article art = self.c_article.getRedirectArticle()
-    #    if not art.good():
-    #        raise RuntimeError("Article is not a redirectArticle")
-    #    article.setup(art)
-    #    return article
-
-
-
 #########################
 #       ZimReader       #
 #########################
@@ -427,7 +343,7 @@ cdef class ZimCreator:
         if not article.can_write:
             raise RuntimeError("Article is not good for writing")
 
-        # Make a shared pointer to ZimArticle from the ZimArticle object (deref internal c_zim_article)
+        # Make a shared pointer to ZimArticle from the ZimArticle object (dereference internal c_zim_article)
         cdef shared_ptr[zim.ZimArticle] art = make_shared[zim.ZimArticle](dereference(article.c_zim_article));
         try:
             self.c_creator.addArticle(art)
@@ -470,31 +386,10 @@ cdef class ZimCreator:
         new_metadata = {pascalize(key): value for key, value in kwargs.items()}
         self._metadata.update(new_metadata)
 
-    def add_art(self, str out_content):
-
-        cdef bytes py_bytes = out_content.encode()
-        cdef char* c_string = py_bytes
-
-        c_zim_art = new zim.ZimArticle(ord("A"),                    # NS
-                                       "".encode(),                 # aid
-                                       "Hola".encode(),             # url
-                                       "JDC HOLA".encode(),         # title
-                                       "text/html".encode(),         # mimeType
-                                       "".encode(),                 # redirectAid
-                                       "".encode(),                 # filename
-                                       True,                        # shouldIndex
-                                       c_string,                    # data buffer
-                                       len(c_string))               # data buffer length
-        # print(c_zim_art.getTitle())
-        #b = c_zim_art.getData()
-        #print(b.data()[:b.size()])
-        cdef shared_ptr[zim.ZimArticle] art = make_shared[zim.ZimArticle](dereference(c_zim_art));
-        self.c_creator.addArticle(art)
-
     def finalise(self):
         if not self._finalised:
-            #TODO uncomment after debug
             self._write_metadata(self.get_metadata())
             self.c_creator.finalise()
+            self._finalised = True
         else:
-            raise RuntimeError("ZimCreator was already finalised")
+            raise RuntimeError("ZimCreator already finalised")