Skip to content

Commit

Permalink
refactor: [FC-0063] Content processors parsing is freed from side eff…
Browse files Browse the repository at this point in the history 
…ects
  • Loading branch information
@myhailo-chernyshov-rg
myhailo-chernyshov-rg committed Feb 22, 2025
1 parent 72265c9 commit 04d1408
Show file tree
Hide file tree
Showing 6 changed files with 73 additions and 81 deletions.
15 changes: 4 additions & 11 deletions src/cc2olx/content_processors/discussion.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,8 @@

from cc2olx import filesystem
from cc2olx.content_processors import AbstractContentProcessor
from cc2olx.content_processors.dataclasses import ContentProcessorContext
from cc2olx.enums import CommonCartridgeResourceType
from cc2olx.models import Cartridge, ResourceFile
from cc2olx.models import ResourceFile
from cc2olx.utils import clean_from_cdata, element_builder


Expand All @@ -17,14 +16,7 @@ class DiscussionContentProcessor(AbstractContentProcessor):

DEFAULT_TEXT = "MISSING CONTENT"

def __init__(self, cartridge: Cartridge, context: ContentProcessorContext) -> None:
super().__init__(cartridge, context)

self._doc: Optional[xml.dom.minidom.Document] = None

def process(self, resource: dict, idref: str) -> Optional[List[xml.dom.minidom.Element]]:
self._doc = xml.dom.minidom.Document()

if content := self._parse(resource):
return self._create_nodes(content)
return None
Expand Down Expand Up @@ -65,11 +57,12 @@ def _create_nodes(self, content: Dict[str, str]) -> List[xml.dom.minidom.Element
"""
Give out <discussion> and <html> OLX nodes.
"""
el = element_builder(self._doc)
doc = xml.dom.minidom.Document()
el = element_builder(doc)

txt = self.DEFAULT_TEXT if content["text"] is None else content["text"]
txt = clean_from_cdata(txt)
html_node = el("html", [self._doc.createCDATASection(txt)], {})
html_node = el("html", [doc.createCDATASection(txt)], {})

discussion_node = el(
"discussion",
Expand Down
34 changes: 17 additions & 17 deletions src/cc2olx/content_processors/html.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,10 +10,8 @@

from cc2olx.constants import FALLBACK_OLX_CONTENT, OLX_STATIC_PATH_TEMPLATE
from cc2olx.content_processors import AbstractContentProcessor
from cc2olx.content_processors.dataclasses import ContentProcessorContext
from cc2olx.content_processors.utils import parse_web_link_content
from cc2olx.enums import CommonCartridgeResourceType
from cc2olx.models import Cartridge
from cc2olx.utils import clean_from_cdata

logger = logging.getLogger()
Expand All @@ -30,26 +28,22 @@ class HtmlContentProcessor(AbstractContentProcessor):

FALLBACK_CONTENT = {"html": FALLBACK_OLX_CONTENT}

def __init__(self, cartridge: Cartridge, context: ContentProcessorContext) -> None:
super().__init__(cartridge, context)

self._doc: Optional[xml.dom.minidom.Document] = None

def process(self, resource: dict, idref: str) -> Optional[List[xml.dom.minidom.Element]]:
self._doc = xml.dom.minidom.Document()

content = self._parse(resource, idref)
return self._create_nodes(content)

def _parse(self, resource: dict, idref: str) -> Dict[str, str]:
"""
Parse content of the resource with the specified identifier.
"""
if resource["type"] == CommonCartridgeResourceType.WEB_CONTENT:
resource_type = resource["type"]

if resource_type == CommonCartridgeResourceType.WEB_CONTENT:
content = self._parse_webcontent(resource, idref)
elif web_link_content := parse_web_link_content(resource, self._cartridge):
elif re.match(CommonCartridgeResourceType.WEB_LINK, resource_type):
web_link_content = parse_web_link_content(resource, self._cartridge)
content = self._transform_web_link_content_to_html(web_link_content)
elif self.is_known_unprocessed_resource_type(resource["type"]):
elif self.is_known_unprocessed_resource_type(resource_type):
content = self.FALLBACK_CONTENT
else:
content = self._parse_not_imported_content(resource)
Expand Down Expand Up @@ -161,20 +155,26 @@ def _create_nodes(self, content: Dict[str, str]) -> List[xml.dom.minidom.Element
video_olx = []
nodes = []
html = content["html"]
doc = xml.dom.minidom.Document()

if self._context.iframe_link_parser:
html, video_olx = self._process_html_for_iframe(html)
html, video_olx = self._process_html_for_iframe(html, doc)
html = clean_from_cdata(html)
txt = self._doc.createCDATASection(html)
txt = doc.createCDATASection(html)

html_node = self._doc.createElement("html")
html_node = doc.createElement("html")
html_node.appendChild(txt)
nodes.append(html_node)

nodes.extend(video_olx)

return nodes

def _process_html_for_iframe(self, html_str: str) -> Tuple[str, List[xml.dom.minidom.Element]]:
def _process_html_for_iframe(
self,
html_str: str,
doc: xml.dom.minidom.Document,
) -> Tuple[str, List[xml.dom.minidom.Element]]:
"""
Parse the iframe with embedded video, to be converted into video xblock.
Expand All @@ -188,7 +188,7 @@ def _process_html_for_iframe(self, html_str: str) -> Tuple[str, List[xml.dom.min
if not iframes:
return html_str, video_olx

video_olx, converted_iframes = self._context.iframe_link_parser.get_video_olx(self._doc, iframes)
video_olx, converted_iframes = self._context.iframe_link_parser.get_video_olx(doc, iframes)
if video_olx:
# If video xblock is present then we modify the HTML to remove the iframe
# hence we need to convert the modified HTML back to string. We also remove
Expand Down
12 changes: 2 additions & 10 deletions src/cc2olx/content_processors/lti.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,7 @@

from cc2olx import filesystem
from cc2olx.content_processors import AbstractContentProcessor
from cc2olx.content_processors.dataclasses import ContentProcessorContext
from cc2olx.enums import CommonCartridgeResourceType
from cc2olx.models import Cartridge
from cc2olx.utils import element_builder, simple_slug
from cc2olx.xml import cc_xml

Expand All @@ -19,14 +17,7 @@ class LtiContentProcessor(AbstractContentProcessor):
DEFAULT_WIDTH = "500"
DEFAULT_HEIGHT = "500"

def __init__(self, cartridge: Cartridge, context: ContentProcessorContext) -> None:
super().__init__(cartridge, context)

self._doc: Optional[xml.dom.minidom.Document] = None

def process(self, resource: dict, idref: str) -> Optional[List[xml.dom.minidom.Element]]:
self._doc = xml.dom.minidom.Document()

if content := self._parse(resource, idref):
self._context.add_lti_consumer_id(content["lti_id"])
return self._create_nodes(content)
Expand Down Expand Up @@ -105,7 +96,8 @@ def _create_nodes(self, content: dict) -> List[xml.dom.minidom.Element]:
"""
Give out <lti_consumer> OLX nodes.
"""
el = element_builder(self._doc)
doc = xml.dom.minidom.Document()
el = element_builder(doc)

custom_parameters = "[{params}]".format(
params=", ".join(
Expand Down
79 changes: 46 additions & 33 deletions src/cc2olx/content_processors/qti.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,9 +14,7 @@

from cc2olx import filesystem
from cc2olx.content_processors import AbstractContentProcessor
from cc2olx.content_processors.dataclasses import ContentProcessorContext
from cc2olx.enums import CommonCartridgeResourceType
from cc2olx.models import Cartridge
from cc2olx.utils import element_builder
from cc2olx.xml import cc_xml

Expand Down Expand Up @@ -61,14 +59,7 @@ class QtiContentProcessor(AbstractContentProcessor):

FIB_PROBLEM_TEXTLINE_SIZE_BUFFER = 10

def __init__(self, cartridge: Cartridge, context: ContentProcessorContext) -> None:
super().__init__(cartridge, context)

self._doc: Optional[xml.dom.minidom.Document] = None

def process(self, resource: dict, idref: str) -> Optional[List[xml.dom.minidom.Element]]:
self._doc = xml.dom.minidom.Document()

if content := self._parse(resource):
return self._create_nodes(content)
return None
Expand Down Expand Up @@ -148,8 +139,8 @@ def _problem_parsers_map(self) -> Dict[QtiQuestionType, Callable[[cc_xml.QtiItem
QtiQuestionType.PATTERN_MATCH: self._parse_pattern_match_problem,
}

@staticmethod
def _parse_fixed_answer_question_responses(
self,
presentation: cc_xml.QtiPresentation,
) -> OrderedDictType[str, Dict[str, Union[bool, str]]]:
"""
Expand Down Expand Up @@ -184,7 +175,8 @@ def _parse_fixed_answer_question_responses(

return responses

def _mark_correct_responses(self, resprocessing: cc_xml.QtiResprocessing, responses: OrderedDict) -> None:
@staticmethod
def _mark_correct_responses(resprocessing: cc_xml.QtiResprocessing, responses: OrderedDict) -> None:
"""
Add the information about correctness to responses data.
Expand Down Expand Up @@ -417,7 +409,8 @@ def _create_nodes(self, content: List[dict]) -> List[xml.dom.minidom.Element]:
if create_problem is None:
raise QtiError('Unknown cc_profile: "{}"'.format(problem_data["cc_profile"]))

problem = create_problem(problem_data)
doc = xml.dom.minidom.Document()
problem = create_problem(problem_data, doc)

# sometimes we might want to have additional items from one CC item
if isinstance(problem, list) or isinstance(problem, tuple):
Expand All @@ -432,7 +425,7 @@ def _problem_creators_map(
self,
) -> Dict[
QtiQuestionType,
Callable[[dict], Union[xml.dom.minidom.Element, Collection[xml.dom.minidom.Element]]],
Callable[[dict, xml.dom.minidom.Document], Union[xml.dom.minidom.Element, Collection[xml.dom.minidom.Element]]],
]:
"""
Provide CC profile value to actual problem node creators mapping.
Expand Down Expand Up @@ -467,50 +460,65 @@ def _create_problem_description(description_html_str: str) -> xml.dom.minidom.El
xml_string = etree.tostring(element)
return xml.dom.minidom.parseString(xml_string).firstChild

def _add_choice(self, parent: xml.dom.minidom.Element, is_correct: bool, text: str) -> None:
def _add_choice(
self,
parent: xml.dom.minidom.Element,
is_correct: bool,
text: str,
doc: xml.dom.minidom.Document,
) -> None:
"""
Append choices to given ``checkboxgroup`` or ``choicegroup`` parent.
"""
choice = self._doc.createElement("choice")
choice = doc.createElement("choice")
choice.setAttribute("correct", "true" if is_correct else "false")
self._set_text(choice, text)
self._set_text(choice, text, doc)
parent.appendChild(choice)

def _set_text(self, node: xml.dom.minidom.Element, new_text: str) -> None:
@staticmethod
def _set_text(node: xml.dom.minidom.Element, new_text: str, doc: xml.dom.minidom.Document) -> None:
"""
Set a node text.
"""
text_node = self._doc.createTextNode(new_text)
text_node = doc.createTextNode(new_text)
node.appendChild(text_node)

def _create_multiple_choice_problem(self, problem_data: dict) -> xml.dom.minidom.Element:
def _create_multiple_choice_problem(
self,
problem_data: dict,
doc: xml.dom.minidom.Document,
) -> xml.dom.minidom.Element:
"""
Create multiple choice problem OLX.
"""
problem = self._doc.createElement("problem")
problem_content = self._doc.createElement("multiplechoiceresponse")
problem = doc.createElement("problem")
problem_content = doc.createElement("multiplechoiceresponse")

problem_description = self._create_problem_description(problem_data["problem_description"])

choice_group = self._doc.createElement("choicegroup")
choice_group = doc.createElement("choicegroup")
choice_group.setAttribute("type", "MultipleChoice")

for choice_data in problem_data["choices"].values():
self._add_choice(choice_group, choice_data["correct"], choice_data["text"])
self._add_choice(choice_group, choice_data["correct"], choice_data["text"], doc)

problem_content.appendChild(problem_description)
problem_content.appendChild(choice_group)
problem.appendChild(problem_content)

return problem

def _create_multiple_response_problem(self, problem_data: dict) -> xml.dom.minidom.Element:
def _create_multiple_response_problem(
self,
problem_data: dict,
doc: xml.dom.minidom.Document,
) -> xml.dom.minidom.Element:
"""
Create multiple response problem OLX.
Set partial_credit to EDC by default.
"""
el = element_builder(self._doc)
el = element_builder(doc)

problem_description = self._create_problem_description(problem_data["problem_description"])

Expand Down Expand Up @@ -540,18 +548,18 @@ def _create_multiple_response_problem(self, problem_data: dict) -> xml.dom.minid
)
return problem

def _create_fib_problem(self, problem_data: dict) -> xml.dom.minidom.Element:
def _create_fib_problem(self, problem_data: dict, doc: xml.dom.minidom.Document) -> xml.dom.minidom.Element:
"""
Create Fill-In-The-Blank problem OLX.
"""
# Track maximum answer length for textline at the bottom
max_answer_length = 0

problem = self._doc.createElement("problem")
problem = doc.createElement("problem")

# Set the primary answer on the stringresponse
# and set the type to case insensitive
problem_content = self._doc.createElement("stringresponse")
problem_content = doc.createElement("stringresponse")
problem_content.setAttribute("answer", problem_data["answer"])
problem_content.setAttribute("type", self._build_fib_problem_type(problem_data))

Expand All @@ -564,15 +572,15 @@ def _create_fib_problem(self, problem_data: dict) -> xml.dom.minidom.Element:
# For any (optional) additional accepted answers, add an
# additional_answer element with that answer
for answer in problem_data.get("additional_answers", []):
additional_answer = self._doc.createElement("additional_answer")
additional_answer = doc.createElement("additional_answer")
additional_answer.setAttribute("answer", answer)
problem_content.appendChild(additional_answer)

if len(answer) > max_answer_length:
max_answer_length = len(answer)

# Add a textline element with the max answer length plus a buffer
textline = self._doc.createElement("textline")
textline = doc.createElement("textline")
textline.setAttribute("size", str(max_answer_length + self.FIB_PROBLEM_TEXTLINE_SIZE_BUFFER))
problem_content.appendChild(textline)

Expand All @@ -595,14 +603,15 @@ def _build_fib_problem_type(problem_data: dict) -> str:
def _create_essay_problem(
self,
problem_data: dict,
doc: xml.dom.minidom.Document,
) -> Union[xml.dom.minidom.Element, Tuple[xml.dom.minidom.Element, xml.dom.minidom.Element]]:
"""
Create an essay problem OLX.
Given parsed essay problem data, returns a openassessment component. If a sample
solution provided, returns that as a HTML block before openassessment.
"""
el = element_builder(self._doc)
el = element_builder(doc)

if any(key in QTI_RESPROCESSING_TYPES for key in problem_data.keys()):
resp_samples = [
Expand Down Expand Up @@ -680,12 +689,16 @@ def _create_essay_problem(
# if a sample solution exists add on top of ora, because
# olx doesn't have a sample solution equivalent.
if problem_data.get("sample_solution"):
child = el("html", self._doc.createCDATASection(problem_data["sample_solution"]))
child = el("html", doc.createCDATASection(problem_data["sample_solution"]))
return child, ora

return ora

def _create_pattern_match_problem(self, problem_data: dict) -> xml.dom.minidom.Element:
def _create_pattern_match_problem(
self,
problem_data: dict,
doc: xml.dom.minidom.Document,
) -> xml.dom.minidom.Element:
"""
Create pattern match problem OLX.
"""
Expand Down
Loading

0 comments on commit 04d1408

Please sign in to comment.