Total Complexity | 65 |
Total Lines | 335 |
Duplicated Lines | 13.13 % |
Changes | 0 |
Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
Complex classes like doorstop.core.publishers.markdown often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
1 | # SPDX-License-Identifier: LGPL-3.0-only |
||
2 | |||
3 | """Functions to publish documents and items.""" |
||
4 | |||
5 | import os |
||
6 | from re import sub |
||
7 | |||
8 | from doorstop import common, settings |
||
9 | from doorstop.core.publishers.base import ( |
||
10 | BasePublisher, |
||
11 | extract_prefix, |
||
12 | format_level, |
||
13 | get_document_attributes, |
||
14 | ) |
||
15 | from doorstop.core.types import is_item, iter_items |
||
16 | |||
17 | log = common.logger(__name__) |
||
18 | INDEX = "index.md" |
||
19 | |||
20 | |||
21 | class MarkdownPublisher(BasePublisher): |
||
22 | """Markdown publisher.""" |
||
23 | |||
24 | def create_index(self, directory, index=INDEX, extensions=(".md",), tree=None): |
||
25 | """Create an markdown index of all files in a directory. |
||
26 | |||
27 | :param directory: directory for index |
||
28 | :param index: filename for index |
||
29 | :param extensions: file extensions to include |
||
30 | :param tree: optional tree to determine index structure |
||
31 | |||
32 | """ |
||
33 | # Get paths for the index index |
||
34 | filenames = [] |
||
35 | for filename in os.listdir(directory): |
||
36 | if filename.endswith(extensions) and filename != INDEX: |
||
37 | filenames.append(os.path.join(filename)) |
||
38 | |||
39 | # Create the index |
||
40 | if filenames: |
||
41 | path = os.path.join(directory, index) |
||
42 | log.info("creating an {}...".format(index)) |
||
43 | lines = self.lines_index(sorted(filenames), tree=tree) |
||
44 | common.write_text("# Requirements index\n" + "\n".join(lines), path) |
||
45 | else: |
||
46 | log.warning("no files for {}".format(index)) |
||
47 | |||
48 | def _index_tree(self, tree, depth): |
||
49 | """Recursively generate markdown index. |
||
50 | |||
51 | :param tree: optional tree to determine index structure |
||
52 | :param depth: depth recursed into tree |
||
53 | """ |
||
54 | |||
55 | depth = depth + 1 |
||
56 | |||
57 | title = get_document_attributes(tree.document)["title"] |
||
58 | prefix = extract_prefix(tree.document) |
||
59 | filename = f"{prefix}.md" |
||
60 | |||
61 | # Tree structure |
||
62 | yield " " * (depth * 2 - 1) + f"* [{prefix}]({filename}) - {title}" |
||
63 | # yield self.table_of_contents(linkify=True, obj=tree.document, depth=depth, heading=False) |
||
64 | for child in tree.children: |
||
65 | yield from self._index_tree(tree=child, depth=depth) |
||
66 | |||
67 | def lines_index(self, filenames, tree=None): |
||
68 | """Yield lines of Markdown for index.md. |
||
69 | |||
70 | :param filenames: list of filenames to add to the index |
||
71 | :param tree: optional tree to determine index structure |
||
72 | """ |
||
73 | if tree: |
||
74 | yield from self._index_tree(tree, depth=0) |
||
75 | |||
76 | # Additional files |
||
77 | if filenames: |
||
78 | yield "" |
||
79 | yield "### Published Documents:" |
||
80 | for filename in filenames: |
||
81 | name = os.path.splitext(filename)[0] |
||
82 | yield " * [{n}]({f})".format(f=filename, n=name) |
||
83 | |||
84 | def create_matrix(self, directory): |
||
85 | """No traceability matrix for Markdown.""" |
||
86 | |||
87 | def format_attr_list(self, item, linkify): |
||
88 | """Create a Markdown attribute list for a heading.""" |
||
89 | return " {{#{u}}}".format(u=item.uid) if linkify else "" |
||
90 | |||
91 | View Code Duplication | def format_ref(self, item): |
|
|
|||
92 | """Format an external reference in Markdown.""" |
||
93 | if settings.CHECK_REF: |
||
94 | path, line = item.find_ref() |
||
95 | path = path.replace("\\", "/") # always use unix-style paths |
||
96 | if line: |
||
97 | return "> `{p}` (line {line})".format(p=path, line=line) |
||
98 | else: |
||
99 | return "> `{p}`".format(p=path) |
||
100 | else: |
||
101 | return "> '{r}'".format(r=item.ref) |
||
102 | |||
103 | View Code Duplication | def format_references(self, item): |
|
104 | """Format an external reference in Markdown.""" |
||
105 | if settings.CHECK_REF: |
||
106 | references = item.find_references() |
||
107 | text_refs = [] |
||
108 | for ref_item in references: |
||
109 | path, line = ref_item |
||
110 | path = path.replace("\\", "/") # always use unix-style paths |
||
111 | |||
112 | if line: |
||
113 | text_refs.append("> `{p}` (line {line})".format(p=path, line=line)) |
||
114 | else: |
||
115 | text_refs.append("> `{p}`".format(p=path)) |
||
116 | |||
117 | return "\n".join(ref for ref in text_refs) |
||
118 | else: |
||
119 | references = item.references |
||
120 | text_refs = [] |
||
121 | for ref_item in references: |
||
122 | path = ref_item["path"] |
||
123 | path = path.replace("\\", "/") # always use unix-style paths |
||
124 | text_refs.append("> '{r}'".format(r=path)) |
||
125 | return "\n".join(ref for ref in text_refs) |
||
126 | |||
127 | def format_links(self, items, linkify): |
||
128 | """Format a list of linked items in Markdown.""" |
||
129 | links = [] |
||
130 | for item in items: |
||
131 | link = self.format_item_link(item, linkify=linkify) |
||
132 | links.append(link) |
||
133 | return ", ".join(links) |
||
134 | |||
135 | def format_item_link(self, item, linkify=True): |
||
136 | """Format an item link in Markdown.""" |
||
137 | if linkify and is_item(item): |
||
138 | link = clean_link("{u}".format(u=self._generate_heading_from_item(item))) |
||
139 | if item.header: |
||
140 | return "[{u} {h}]({p}.md#{l})".format( |
||
141 | u=item.uid, l=link, h=item.header, p=item.document.prefix |
||
142 | ) |
||
143 | return "[{u}]({p}.md#{l})".format( |
||
144 | u=item.uid, l=link, p=item.document.prefix |
||
145 | ) |
||
146 | else: |
||
147 | return str(item.uid) # if not `Item`, assume this is an `UnknownItem` |
||
148 | |||
149 | def format_label_links(self, label, links, linkify): |
||
150 | """Join a string of label and links with formatting.""" |
||
151 | if linkify: |
||
152 | return "*{lb}* {ls}".format(lb=label, ls=links) |
||
153 | else: |
||
154 | return "*{lb} {ls}*".format(lb=label, ls=links) |
||
155 | |||
156 | def table_of_contents(self, linkify=None, obj=None): |
||
157 | """Generate a table of contents for a Markdown document.""" |
||
158 | |||
159 | toc = "### Table of Contents\n\n" |
||
160 | toc_doc = obj |
||
161 | |||
162 | for item in iter_items(toc_doc): |
||
163 | if item.depth == 1: |
||
164 | prefix = " * " |
||
165 | else: |
||
166 | prefix = " " * (item.depth - 1) |
||
167 | prefix += "* " |
||
168 | |||
169 | # Check if item has the attribute heading. |
||
170 | if item.heading: |
||
171 | lines = item.text.splitlines() |
||
172 | heading = lines[0] if lines else "" |
||
173 | elif item.header: |
||
174 | heading = "{h}".format(h=item.header) |
||
175 | else: |
||
176 | heading = item.uid |
||
177 | |||
178 | if settings.PUBLISH_HEADING_LEVELS: |
||
179 | level = format_level(item.level) |
||
180 | lbl = "{lev} {h}".format(lev=level, h=heading) |
||
181 | else: |
||
182 | lbl = heading |
||
183 | |||
184 | if linkify: |
||
185 | link = clean_link(self._generate_heading_from_item(item)) |
||
186 | line = "{p}[{lbl}](#{l})\n".format(p=prefix, lbl=lbl, l=link) |
||
187 | else: |
||
188 | line = "{p}{lbl}\n".format(p=prefix, lbl=lbl) |
||
189 | toc += line |
||
190 | return toc |
||
191 | |||
192 | def lines(self, obj, **kwargs): |
||
193 | """Yield lines for a Markdown report. |
||
194 | |||
195 | :param obj: Item, list of Items, or Document to publish |
||
196 | :param linkify: turn links into hyperlinks |
||
197 | |||
198 | :return: iterator of lines of text |
||
199 | |||
200 | """ |
||
201 | linkify = kwargs.get("linkify", False) |
||
202 | toc = kwargs.get("toc", False) |
||
203 | if toc: |
||
204 | yield self.table_of_contents(linkify=linkify, obj=obj) |
||
205 | |||
206 | yield from self._lines_markdown(obj, **kwargs) |
||
207 | |||
208 | def _generate_heading_from_item(self, item, to_html=False): |
||
209 | """Generate a heading from an item in a consistent way for Markdown. |
||
210 | |||
211 | This ensures that references between documents are consistent. |
||
212 | """ |
||
213 | result = "" |
||
214 | heading = "#" * item.depth |
||
215 | level = format_level(item.level) |
||
216 | if item.heading: |
||
217 | text_lines = item.text.splitlines() |
||
218 | if item.header: |
||
219 | text_lines.insert(0, item.header) |
||
220 | # Level and Text |
||
221 | if settings.PUBLISH_HEADING_LEVELS: |
||
222 | standard = "{h} {lev} {t}".format( |
||
223 | h=heading, lev=level, t=text_lines[0] if text_lines else "" |
||
224 | ) |
||
225 | else: |
||
226 | standard = "{h} {t}".format( |
||
227 | h=heading, t=text_lines[0] if text_lines else "" |
||
228 | ) |
||
229 | attr_list = self.format_attr_list(item, True) |
||
230 | result = standard + attr_list |
||
231 | else: |
||
232 | uid = item.uid |
||
233 | if settings.ENABLE_HEADERS: |
||
234 | if item.header: |
||
235 | if to_html: |
||
236 | uid = "{h} <small>{u}</small>".format(h=item.header, u=item.uid) |
||
237 | else: |
||
238 | uid = "{h} _{u}_".format(h=item.header, u=item.uid) |
||
239 | else: |
||
240 | uid = "{u}".format(u=item.uid) |
||
241 | |||
242 | # Level and UID |
||
243 | if settings.PUBLISH_BODY_LEVELS: |
||
244 | standard = "{h} {lev} {u}".format(h=heading, lev=level, u=uid) |
||
245 | else: |
||
246 | standard = "{h} {u}".format(h=heading, u=uid) |
||
247 | |||
248 | attr_list = self.format_attr_list(item, True) |
||
249 | result = standard + attr_list |
||
250 | return result |
||
251 | |||
252 | def _lines_markdown(self, obj, **kwargs): |
||
253 | """Yield lines for a Markdown report. |
||
254 | |||
255 | :param obj: Item, list of Items, or Document to publish |
||
256 | :param linkify: turn links into hyperlinks |
||
257 | |||
258 | :return: iterator of lines of text |
||
259 | |||
260 | """ |
||
261 | linkify = kwargs.get("linkify", False) |
||
262 | to_html = kwargs.get("to_html", False) |
||
263 | for item in iter_items(obj): |
||
264 | # Create iten heading. |
||
265 | complete_heading = self._generate_heading_from_item(item, to_html=to_html) |
||
266 | yield complete_heading |
||
267 | |||
268 | # Text |
||
269 | if item.text: |
||
270 | yield "" # break before text |
||
271 | yield from item.text.splitlines() |
||
272 | |||
273 | # Reference |
||
274 | if item.ref: |
||
275 | yield "" # break before reference |
||
276 | yield self.format_ref(item) |
||
277 | |||
278 | # Reference |
||
279 | if item.references: |
||
280 | yield "" # break before reference |
||
281 | yield self.format_references(item) |
||
282 | |||
283 | # Parent links |
||
284 | View Code Duplication | if item.links: |
|
285 | yield "" # break before links |
||
286 | items2 = item.parent_items |
||
287 | if settings.PUBLISH_CHILD_LINKS: |
||
288 | label = "Parent links:" |
||
289 | else: |
||
290 | label = "Links:" |
||
291 | links = self.format_links(items2, linkify) |
||
292 | label_links = self.format_label_links(label, links, linkify) |
||
293 | yield label_links |
||
294 | |||
295 | # Child links |
||
296 | if settings.PUBLISH_CHILD_LINKS: |
||
297 | items2 = item.find_child_items() |
||
298 | if items2: |
||
299 | yield "" # break before links |
||
300 | label = "Child links:" |
||
301 | links = self.format_links(items2, linkify) |
||
302 | label_links = self.format_label_links(label, links, linkify) |
||
303 | yield label_links |
||
304 | |||
305 | # Add custom publish attributes |
||
306 | if item.document and item.document.publish: |
||
307 | header_printed = False |
||
308 | for attr in item.document.publish: |
||
309 | if not item.attribute(attr): |
||
310 | continue |
||
311 | if not header_printed: |
||
312 | header_printed = True |
||
313 | yield "" |
||
314 | yield "| Attribute | Value |" |
||
315 | yield "| --------- | ----- |" |
||
316 | yield "| {} | {} |".format(attr, item.attribute(attr)) |
||
317 | yield "" |
||
318 | |||
319 | yield "" # break between items |
||
320 | |||
321 | |||
322 | def clean_link(uid): |
||
323 | """Clean a UID for use in a link. |
||
324 | |||
325 | 1. Strip leading # and spaces. |
||
326 | 2. Only smallcaps are allowed. |
||
327 | 3. Spaces are replaced with hyphens. |
||
328 | 5. All other special characters are removed. |
||
329 | """ |
||
330 | uid = sub(r"^#*\s*", "", uid) |
||
331 | uid = uid.lower() |
||
332 | uid = uid.replace(" ", "-") |
||
333 | uid = sub("[^a-z0-9-]", "", uid) |
||
334 | return uid |
||
335 |