Refactor statement handling

mypy.ini

@@ -1,5 +1,6 @@
 [mypy]
-ignore_missing_imports = True
+ignore_missing_imports = False
+follow_untyped_imports = True
 install_types = True
 check_untyped_defs = True
 ignore_errors = False

problemtools/ProblemPlasTeX/ProblemsetMacros.py

@@ -109,6 +109,7 @@ def invoke(self, tex):
         res = super().invoke(tex)
 
         # Overcome plasTeX bug by looking for love in the right place
+        assert self.ownerDocument is not None  # Keep mypy happy
         basetex = self.ownerDocument.userdata['base_tex_instance']
         f = self.attributes['file']
         ext = self.ownerDocument.userdata.getPath('packages/graphicx/extensions', ['.png', '.jpg', '.jpeg', '.gif', '.pdf'])

problemtools/ProblemPlasTeX/__init__.py

@@ -83,7 +83,7 @@ class ProblemRenderer(Renderer):
     imageTypes = ['.png', '.jpg', '.jpeg', '.gif']
     vectorImageTypes = ['.svg']
 
-    def render(self, document):
+    def render(self, document, postProcess=None):
         templatepaths = [
             os.path.join(os.path.dirname(__file__), '../templates/html'),
             os.path.join(os.path.dirname(__file__), '../../templates/html'),

problemtools/ProblemPlasTeX/graphicx.py

@@ -1,5 +1,5 @@
 import plasTeX.Packages.graphics as graphics
-from ProblemsetMacros import _graphics_command, clean_width
+from problemtools.ProblemPlasTeX.ProblemsetMacros import _graphics_command, clean_width
 
 # Reimplementation of graphicx package because plasTeX is broken and
 # annoying.

problemtools/ProblemPlasTeX/listingsutf8.py

@@ -18,6 +18,7 @@ def read_file(self, filename) -> str:
 
     def invoke(self, tex) -> None:
         super().invoke(tex)
+        assert self.ownerDocument is not None  # Keep mypy happy
         basetex = self.ownerDocument.userdata['base_tex_instance']
         f = self.attributes['file']
         # Maybe more paths to look in?

problemtools/md2html.py

@@ -14,28 +14,19 @@
 from . import statement_util
 
 
-def convert(problem: str, options: argparse.Namespace) -> bool:
+def convert(problem_root: Path, options: argparse.Namespace, statement_file: Path) -> bool:
     """Convert a Markdown statement to HTML
 
     Args:
         problem: path to problem directory
         options: command-line arguments. See problem2html.py
     """
-    problembase = os.path.splitext(os.path.basename(problem))[0]
-    destfile = string.Template(options.destfile).safe_substitute(problem=problembase)
+    destfile = string.Template(options.destfile).safe_substitute(problem=problem_root.name)
 
-    statement_path = statement_util.find_statement(problem, extension='md', language=options.language)
-
-    if statement_path is None:
-        raise FileNotFoundError('No markdown statement found')
-
-    if not os.path.isfile(statement_path):
-        raise FileNotFoundError(f'Error! {statement_path} does not exist')
-
-    command = ['pandoc', statement_path, '-t', 'html', '--mathjax']
+    command = ['pandoc', str(statement_file), '-t', 'html', '--mathjax']
     statement_html = subprocess.run(command, capture_output=True, text=True, shell=False, check=True).stdout
 
-    statement_html = sanitize_html(problem, statement_html)
+    statement_html = sanitize_html(statement_file.parent, statement_html)
 
     templatepaths = [
         os.path.join(os.path.dirname(__file__), 'templates/markdown_html'),
@@ -51,17 +42,17 @@ def convert(problem: str, options: argparse.Namespace) -> bool:
     with open(Path(templatepath) / 'default-layout.html', 'r', encoding='utf-8') as template_file:
         template = template_file.read()
 
-    problem_name = statement_util.get_yaml_problem_name(problem, options.language)
+    problem_name = statement_util.get_yaml_problem_name(problem_root, options.language)
     substitution_params = {
         'statement_html': statement_html,
         'language': options.language,
         'title': html.escape(problem_name) if problem_name else 'Missing problem name',
-        'problemid': html.escape(problembase),
+        'problemid': html.escape(problem_root.name),
     }
 
     statement_html = template % substitution_params
 
-    samples = statement_util.format_samples(problem)
+    samples = statement_util.format_samples(problem_root)
     # Insert samples at {{nextsample}} and {{remainingsamples}}
     statement_html, remaining_samples = statement_util.inject_samples(statement_html, samples)
 
@@ -84,7 +75,7 @@ def convert(problem: str, options: argparse.Namespace) -> bool:
     return True
 
 
-def sanitize_html(problem: str, statement_html: str):
+def sanitize_html(statement_dir: Path, statement_html: str) -> str:
     # Allow footnote ids (the anchor points you jump to)
     def is_fn_id(s):
         pattern_id_top = r'^fn\d+$'
@@ -93,18 +84,6 @@ def is_fn_id(s):
 
     allowed_classes = ('sample', 'problemheader', 'problembody', 'sampleinteractionwrite', 'sampleinteractionread')
 
-    def is_image_valid(problem_root: str, img_src: str) -> str | None:
-        # Check that the image exists and uses an allowed extension
-        extension = Path(img_src).suffix
-        # TODO: fix svg sanitization and allow svg
-        if extension not in statement_util.ALLOWED_IMAGE_EXTENSIONS:
-            return f'Unsupported image extension {extension} for image {img_src}'
-
-        source_file = Path(problem_root) / 'statement' / img_src
-        if not source_file.exists():
-            return f'Resource file {img_src} not found in statement'
-        return None
-
     # Annoying: nh3 will ignore exceptions in attribute_filter
     image_fail_reason: str | None = None
 
@@ -120,12 +99,13 @@ def attribute_filter(tag, attribute, value):
         if tag in ('li', 'a') and attribute == 'id' and is_fn_id(value):
             return value
         if tag == 'img' and attribute == 'src':
-            fail = is_image_valid(problem, value)
-            if fail:
+            try:
+                statement_util.assert_image_is_valid(statement_dir, value)
+            except Exception as e:
                 nonlocal image_fail_reason
-                image_fail_reason = fail
+                image_fail_reason = str(e)
                 return None
-            copy_image(problem, value)
+            copy_image(statement_dir, value)
             return value
         return None
 
@@ -154,16 +134,14 @@ def attribute_filter(tag, attribute, value):
     return statement_html
 
 
-def copy_image(problem_root: str, img_src: str) -> None:
+def copy_image(statement_dir: Path, img_src: str) -> None:
     """Copy image to output directory
 
     Args:
-        problem_root: the root of the problem directory
+        statement_dir: the directory with problem statement files
         img_src: the image source as in the Markdown statement
     """
 
-    source_name = os.path.join(problem_root, 'statement', img_src)
-
     if os.path.isfile(img_src):  # already copied
         return
-    shutil.copyfile(source_name, img_src)
+    shutil.copyfile(statement_dir / img_src, img_src)

problemtools/problem2html.py

@@ -1,25 +1,29 @@
 #! /usr/bin/env python3
 # -*- coding: utf-8 -*-
-import re
+import argparse
 import os.path
+import re
 import string
-import argparse
 import subprocess
+import sys
+from pathlib import Path
 
 from . import tex2html
 from . import md2html
 from . import statement_util
 
 
-def convert(options: argparse.Namespace) -> None:
-    problem = os.path.realpath(options.problem)
+def convert(options: argparse.Namespace, force_statement_file: Path | None = None) -> None:
+    problem_root = Path(options.problem).resolve(strict=True)
 
-    if not os.path.isdir(problem):
-        raise Exception(f'Problem does not exist: {problem}')
+    if force_statement_file:  # Used by verifyproblem to test rendering even if there are multiple statements in a language
+        statement_file = force_statement_file
+    else:
+        statement_file = statement_util.find_statement(problem_root, options.language)
 
-    problembase = os.path.splitext(os.path.basename(problem))[0]
-    destdir = string.Template(options.destdir).safe_substitute(problem=problembase)
-    destfile = string.Template(options.destfile).safe_substitute(problem=problembase)
+    destdir = string.Template(options.destdir).safe_substitute(problem=problem_root.name)
+    destfile = string.Template(options.destfile).safe_substitute(problem=problem_root.name)
+    origcwd = os.getcwd()
 
     # Go to destdir
     if destdir:
@@ -30,13 +34,13 @@ def convert(options: argparse.Namespace) -> None:
     try:
         if not options.quiet:
             print('Rendering!')
-
-        origcwd = os.getcwd()
-
-        if statement_util.find_statement_extension(problem, options.language) == 'tex':
-            tex2html.convert(problem, options)
-        else:
-            md2html.convert(problem, options)
+        match statement_file.suffix:
+            case '.md':
+                md2html.convert(problem_root, options, statement_file)
+            case '.tex':
+                tex2html.convert(problem_root, options, statement_file)
+            case _:
+                raise NotImplementedError('Unsupported file type, expected md or tex: {statement_file.name}')
 
         if options.tidy:
             with open(os.devnull, 'w') as devnull:
@@ -88,13 +92,12 @@ def get_parser() -> argparse.ArgumentParser:
     )
     parser.add_argument('-d', '--dest-dir', dest='destdir', help='output directory', default='${problem}_html')
     parser.add_argument('-f', '--dest-file', dest='destfile', help='output file name', default='index.html')
-    parser.add_argument('-l', '--language', dest='language', help='choose alternate language (2-letter code)', default=None)
+    parser.add_argument('-l', '--language', dest='language', help='choose language (2-letter code)', default='en')
     parser.add_argument(
         '-L', '--log-level', dest='loglevel', help='set log level (debug, info, warning, error, critical)', default='warning'
     )
     parser.add_argument('-q', '--quiet', dest='quiet', action='store_true', help='quiet', default=False)
     parser.add_argument('-i', '--imgbasedir', dest='imgbasedir', default='')
-    parser.add_argument('-v', '--format-version', dest='format_version', help='choose format version', default='automatic')
     parser.add_argument('problem', help='the problem to convert')
 
     return parser
@@ -103,7 +106,11 @@ def get_parser() -> argparse.ArgumentParser:
 def main() -> None:
     parser = get_parser()
     options = parser.parse_args()
-    convert(options)
+    try:
+        convert(options)
+    except Exception as e:
+        print(e)
+        sys.exit(1)
 
 
 if __name__ == '__main__':