Compare commits
No commits in common. "a681d21f5623ba12675cccf36908c89682e2e52c" and "6d01b2d6830b9d03909485b7db75182bfafebe6f" have entirely different histories.
a681d21f56
...
6d01b2d683
12
Makefile
12
Makefile
@ -77,7 +77,7 @@ WINDOWS_ICON_SIZES = 150x150
|
||||
# all android-chrome-XXxXX.png sizes
|
||||
ANDROID_ICON_SIZES = 192x192 512x512
|
||||
# all favicon-XXxXX.png sizes
|
||||
FAVICON_ICON_SIZES = 16x16 32x32 48x48
|
||||
FAVICON_ICON_SIZES = 16x16 32x32 64x64
|
||||
|
||||
# THUMBNAILS:
|
||||
# thumbnails for all resource files having an extension in THUMB_FOR_TYPES will be generated and placed relative to THUMB_OUT_DIR
|
||||
@ -220,10 +220,10 @@ FMT_OUT_THUMB ="\e[1;34mGenerating thumbnail\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s
|
||||
FMT_OUT_SITEMAP ="\e[1;34mGenerating sitemap\e[0m: \e[1;35m%s\e[0m\n"
|
||||
FMT_OUT_FAVICON ="\e[1;34mGenerating favicon\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s\e[0m\n"
|
||||
FMT_OUT_OTHER ="\e[1;34mBuilding\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s\e[0m\n"
|
||||
FMT_OUT_ML_HTML ="\e[1;34mBuilding html\e[0m in lang \e[1;34m%s\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s\e[0m\n"
|
||||
FMT_OUT_ML_OTHER ="\e[1;34mBuilding\e[0m in lang \e[1;34m%s\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s\e[0m\n"
|
||||
# .SUFFIXES:
|
||||
# .SUFFIXES: .html .md
|
||||
FMT_OUT_ML_HTML="\e[1;34mBuilding html\e[0m in lang \e[1;34m%s\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s\e[0m\n"
|
||||
FMT_OUT_ML_OTHER="\e[1;34mBuilding\e[0m in lang \e[1;34m%s\e[0m: \e[1;33m%s\e[0m at \e[1;35m%s\e[0m\n"
|
||||
.SUFFIXES:
|
||||
.SUFFIXES: .html .md
|
||||
|
||||
.PHONY: default normal multilang resources sitemap favicons thumbnails print start stop clean cleaner
|
||||
|
||||
@ -364,7 +364,7 @@ stop:
|
||||
killall nginx
|
||||
|
||||
clean:
|
||||
-@rm $(OUT_FLS) $(ML_OUT_FLS) $(SITEMAP_TEMP_FILE) $(SITEMAP) 2>/dev/null
|
||||
-@rm $(OUT_FLS) $(ML_OUT_FLS) $(SITEMAP_TEMP_FILE) $(SITEMAP) $(FAVICONS) 2>/dev/null
|
||||
-@rm -r $(DEP_DIR) 2>/dev/null
|
||||
|
||||
cleaner:
|
||||
|
13
README.md
13
README.md
@ -20,6 +20,7 @@ refer to the article [on my website](https://quintern.xyz/en/software/buwuma.htm
|
||||
<!--
|
||||
#command everything here is an argument
|
||||
#anothercommand more arguments
|
||||
While this is a comment right now, it will be UNCOMMENTED in the after the preprocessor finishes!
|
||||
#comment This will be a single line html comment after the preprocessor finishes.
|
||||
-->
|
||||
```
|
||||
@ -123,6 +124,8 @@ Any string
|
||||
**Return Value**:
|
||||
The argument in comment tags
|
||||
|
||||
This can be useful in multi-line comments that contain other commands: In that case, the comment tags will be removed and each command replaced with
|
||||
its return value, so if you want to just have commented text in there you can use `#comment`
|
||||
|
||||
### uncomment
|
||||
Uncomment the comment.
|
||||
@ -142,7 +145,7 @@ This can be useful when you want to look at the unprocessed html without variabl
|
||||
|
||||
### conditionals
|
||||
To turn on or off entire blocks, `if`, `elif` can `else` be used.
|
||||
These commands can not be nested.
|
||||
These commands can not be nested and must not appear in multi-line comments.
|
||||
Logical and `&&` and logical or `||` can be used to chain conditions.
|
||||
If a condition is true, the corresponding block is included while all other blocks are deleted.
|
||||
|
||||
@ -183,7 +186,7 @@ The generated sidenav
|
||||
|
||||
|
||||
#### `section`
|
||||
Group all following entries in named section. `section` may not appear in conditional blocks.
|
||||
Group all following entries in named section. `section` may not appear in conditional blocks and multiline comments.
|
||||
|
||||
**Argument**:
|
||||
The name of the section
|
||||
@ -275,9 +278,9 @@ Empty string
|
||||
|
||||
|
||||
## Pitfalls
|
||||
- The `include` command must not be in the last line of the file
|
||||
- The `#include` command must not be in the last line of the file
|
||||
- The `#include` command can not be in multi-line comment if the included file also contains comments
|
||||
- `#if`, `#elif`, `#else` and `#endif` must not be in multi-line comments
|
||||
- The maps in `set` must have **at least 2** options
|
||||
- The `section` commands must not be in a conditional block
|
||||
- The conditionals must not be neseted
|
||||
- If you want to use variables in markdown, you have to escape the `#` with a backslash, so `#$(var)` becomes `\#$(var)`
|
||||
- You can not use the `return` command from within the arguments of other commands. Commands are executed in order, so `return` will end up as argument of the first command and thus never be executed
|
||||
|
@ -16,13 +16,13 @@ TODO:
|
||||
************************************************************ SETTINGS ************************************************************
|
||||
"""
|
||||
sidenav_format = """\
|
||||
<div class="sidenav">
|
||||
<ul>
|
||||
<li class="menudrop">☰</li>
|
||||
#sidenav-content
|
||||
</ul>
|
||||
</div>
|
||||
"""
|
||||
<div class="sidenav">
|
||||
<ul>
|
||||
<li class="menudrop">☰</li>
|
||||
#sidenav-content
|
||||
</ul>
|
||||
</div>
|
||||
"""
|
||||
sidenav_content_link = "<li class=\"sidenav_link\"><a href=\"#link\">#name</a></li>"
|
||||
sidenav_content_section = "<li class=\"sidenav_section\">#name</li>"
|
||||
|
||||
@ -51,7 +51,7 @@ re_set_map_alt = r"([a-zA-Z0-9_]+) *\? *\{( *(?:[a-zA-Z0-9_*]+ *: *[^;]* *; *)+[
|
||||
re_variable_use = r"#\$\(([a-zA-Z0-9_]+)\)"
|
||||
|
||||
""" only in comments """
|
||||
re_preprocessor_command = r"[\t ]*#([a-zA-Z]+) *(.*)[\t ]*"
|
||||
re_preprocessor_command = r"#([a-zA-Z]+) *(.*) *"
|
||||
|
||||
# https://www.w3.org/TR/NOTE-datetime
|
||||
re_w3cdate = r"\d{4}-(?)]-\d{2}"
|
||||
@ -84,36 +84,20 @@ current_file_url = ""
|
||||
"""
|
||||
************************************************************ UTILITY ************************************************************
|
||||
"""
|
||||
|
||||
RED = '\033[91m'
|
||||
GREEN = '\033[92m'
|
||||
YELLOW = '\033[93m'
|
||||
BLUE = '\033[94m'
|
||||
MAGENTA = '\033[95m'
|
||||
CYAN = '\033[96m'
|
||||
GRAY = '\033[97m'
|
||||
RESET = '\033[0m'
|
||||
BOLD = '\033[1m'
|
||||
WHITE = '\033[37m'
|
||||
|
||||
|
||||
DEBUG = False
|
||||
def pdebug(*args, **keys):
|
||||
fname, *_args = args
|
||||
if DEBUG: print(f"{CYAN}{fname}{GRAY}", *_args, RESET, **keys)
|
||||
if DEBUG: print(*args, **keys)
|
||||
|
||||
TRACE = False
|
||||
def ptrace(*args, **keys):
|
||||
fname, *_args = args
|
||||
if TRACE: print(f"{BLUE}{fname}{GRAY}", *_args, RESET, **keys)
|
||||
if TRACE: print(*args, **keys)
|
||||
|
||||
def error(*args, level:int=exit_on_error_level, exit_code:int=1, **keys):
|
||||
fname, *_args = args
|
||||
if level >= exit_on_error_level:
|
||||
print(f"{RED}ERROR: {fname}{RESET}", *_args, RESET, **keys)
|
||||
print(f"ERROR:", *args, **keys)
|
||||
exit(exit_code)
|
||||
else:
|
||||
print(f"{YELLOW}WARNING: {fname}{RESET}", *_args, RESET, **keys)
|
||||
print(f"WARNING:", *args, **keys)
|
||||
|
||||
def line_is_link_to_path(line, path):
|
||||
# check if the line is a link to html thats currently being processed
|
||||
@ -144,11 +128,11 @@ def evaluate_condition(input_string) -> bool:
|
||||
words[i] = '"' + words[i].replace('"', r'\"') + '"'
|
||||
|
||||
condition = "".join(words).replace("&&", " and ").replace("||", " or ")
|
||||
ptrace("evaluate_conditon", f"Evaluating condition {condition}")
|
||||
ptrace(f"> Evaluating condition {condition}")
|
||||
try:
|
||||
return eval(condition)
|
||||
except SyntaxError:
|
||||
error("evaluate_conditon", f"Pythonized condition is invalid: {condition}", level=error_levels["light"])
|
||||
error(f"Pythonized condition is invalid: {condition}", level=error_levels["light"])
|
||||
return False
|
||||
|
||||
"""
|
||||
@ -169,19 +153,19 @@ class Sitemap:
|
||||
try:
|
||||
priority = float(priority)
|
||||
except ValueError:
|
||||
error("Sitemap.set_priority", f"invalid priority: '{priority}'", level=error_levels["serious"])
|
||||
error(f"Sitemap: invalid priority: '{priority}'", level=error_levels["serious"])
|
||||
if not (type(priority) == float and 0.0 <= priority and priority <= 1.0):
|
||||
error("Sitemap.set_priority", f"invalid priority: '{priority}'", level=error_levels["serious"])
|
||||
error(f"Sitemap: invalid priority: '{priority}'", level=error_levels["serious"])
|
||||
self.priority = priority
|
||||
|
||||
def set_changefreq(self, changefreq):
|
||||
if not (type(changefreq) == str and changefreq in ["always", "hourly", "daily", "weekly", "monthly", "yearly", "never"]):
|
||||
error("Sitemap.set_changefreq", f"invalid changefreq: '{changefreq}'", level=error_levels["serious"])
|
||||
error(f"Sitemap: invalid changefreq: '{changefreq}'", level=error_levels["serious"])
|
||||
self.changefreq = changefreq
|
||||
|
||||
def set_lastmod(self, lastmod):
|
||||
if not (type(lastmod) == str and re.fullmatch(re_w3cdate, lastmod)):
|
||||
error("Sitemap.set_lastmod", f"invalid lastmod: '{lastmod}'", level=error_levels["serious"])
|
||||
error(f"Sitemap: invalid lastmod: '{lastmod}'", level=error_levels["serious"])
|
||||
self.lastmod = lastmod
|
||||
|
||||
def get_entry(self):
|
||||
@ -213,7 +197,7 @@ class Sitemap:
|
||||
|
||||
if 0 < space and space < len(args) - 1:
|
||||
cmd_args = args[space+1:].strip(" ")
|
||||
pdebug("cmd_sitemap", f"cmd='{cmd}' cmd_args='{cmd_args}'")
|
||||
pdebug(f"cmd_sitemap: cmd='{cmd}' cmd_args='{cmd_args}'")
|
||||
if not current_file_url in Sitemap.urls:
|
||||
Sitemap.urls[current_file_url] = Sitemap()
|
||||
if cmd == "include":
|
||||
@ -228,8 +212,8 @@ class Sitemap:
|
||||
elif cmd == "lastmod":
|
||||
Sitemap.urls[current_file_url].set_lastmod(cmd_args)
|
||||
else:
|
||||
error("cmd_sitemap", f"Invalid command '{cmd}'", error_levels["serious"])
|
||||
ptrace("cmd_sitemap", f"Sitemap[{current_file_url}] is now: {Sitemap.urls[current_file_url]}")
|
||||
error(f"cmd_sitemap: Invalid command '{cmd}'", error_levels["serious"])
|
||||
ptrace(f"Sitemap[{current_file_url}] is now: {Sitemap.urls[current_file_url]}")
|
||||
return ""
|
||||
|
||||
|
||||
@ -263,7 +247,7 @@ class Sidenav:
|
||||
Sidenav.skip_next = True
|
||||
@staticmethod
|
||||
def generate() -> str:
|
||||
pdebug("Sidenav.generate", f"found the following entries: {Sidenav.entries}")
|
||||
pdebug(f"Sidenav.generate(): found the following entries: {Sidenav.entries}")
|
||||
sidenav:list[str] = sidenav_format.split('\n')
|
||||
content_i = -1
|
||||
for i in range(len(sidenav)): # find in which line the entries need to be placed
|
||||
@ -271,16 +255,16 @@ class Sidenav:
|
||||
content_i = i
|
||||
break
|
||||
if content_i >= 0:
|
||||
indent = sidenav.pop(content_i).replace("#sidenav-content", "")
|
||||
sidenav.pop(content_i)
|
||||
added_links = []
|
||||
for i in reversed(range(len(Sidenav.entries))):
|
||||
entry = Sidenav.entries[i]
|
||||
if entry[0] == Sidenav.LINK:
|
||||
if entry[2] in added_links: continue # no duplicates
|
||||
added_links.append(entry[2])
|
||||
sidenav.insert(content_i, indent + sidenav_content_link.replace("#name", entry[1]).replace("#link", entry[2]))
|
||||
sidenav.insert(content_i, sidenav_content_link.replace("#name", entry[1]).replace("#link", entry[2]))
|
||||
else:
|
||||
sidenav.insert(content_i, indent + sidenav_content_section.replace("#name", entry[1]))
|
||||
sidenav.insert(content_i, sidenav_content_section.replace("#name", entry[1]))
|
||||
sidenav_s = ""
|
||||
for line in sidenav: sidenav_s += line + "\n" # cant use "".join because of newlines
|
||||
return sidenav_s
|
||||
@ -293,7 +277,7 @@ class Sidenav:
|
||||
cmd_args = ""
|
||||
if 0 < space and space < len(args) - 1:
|
||||
cmd_args = args[space+1:].strip(" ")
|
||||
pdebug("cmd_sidenav", f"cmd='{cmd}' cmd_args='{cmd_args}'")
|
||||
pdebug(f"cmd_sidenav: cmd='{cmd}' cmd_args='{cmd_args}'")
|
||||
if cmd == "skip":
|
||||
Sidenav.skipNext()
|
||||
elif cmd == "section":
|
||||
@ -305,11 +289,11 @@ class Sidenav:
|
||||
if match:
|
||||
Sidenav.addEntry(match.groups()[1], match.groups()[0])
|
||||
else:
|
||||
error("cmd_sidenav", f"Invalid argument for command 'custom': '{cmd_args}'", level=error_levels["light"])
|
||||
error(f"cmd_sidenav: Invalid argument for command 'custom': '{cmd_args}'", level=error_levels["light"])
|
||||
elif cmd == "include":
|
||||
return Sidenav.generate()
|
||||
else:
|
||||
error("cmd_sidenav", f"Invalid command: '{cmd}'", level=error_levels["light"])
|
||||
error(f"cmd_sidenav: Invalid command: '{cmd}'", level=error_levels["light"])
|
||||
|
||||
return ""
|
||||
|
||||
@ -324,7 +308,7 @@ into the source file at the place where the command was.
|
||||
"""
|
||||
def cmd_include(args: str, variables:dict[str, str]={}) -> str:
|
||||
args = args.split(' ')
|
||||
pdebug("cmd_include", f"args='{args}', variables='{variables}'")
|
||||
pdebug(f"cmd_include: args='{args}', variables='{variables}'")
|
||||
filename = args[0]
|
||||
content = ""
|
||||
try:
|
||||
@ -335,17 +319,16 @@ def cmd_include(args: str, variables:dict[str, str]={}) -> str:
|
||||
p = HTMLParser(content, {})
|
||||
p.pos["start"] = p.pos["end"] = -1
|
||||
while p.i < len(p): # at start of new line or end of comment
|
||||
p.find_line_end()
|
||||
ptrace("cmd_include", f"Processing at i={p.i} in line {pos2line(p.file, p.i)}: '{p[p.i:p.pos['line_end']]}'")
|
||||
p.next_line()
|
||||
ptrace(f"cmd_include: Processing at i={p.i} in line {pos2line(p.file, p.i)}")
|
||||
if not p.find_comment_begin(): continue
|
||||
if not p.find_comment_end(): continue
|
||||
p.replace_multiline_comments()
|
||||
|
||||
match = p.find_command()
|
||||
if match:
|
||||
command = match.groups()[0]
|
||||
cmd_args = match.groups()[1].replace('\t', ' ').strip(' ')
|
||||
pdebug("cmd_include", f"Found command '{command}' with args '{cmd_args}'")
|
||||
pdebug(f"cmd_include Found command '{command}' with args '{cmd_args}'")
|
||||
if command == "section":
|
||||
if cmd_args.startswith(target_section):
|
||||
p.pos["start"] = max(p.pos["cmt_end"] + len(COMMENT_END), p.pos["line_end"] + 1)
|
||||
@ -367,16 +350,16 @@ def cmd_include(args: str, variables:dict[str, str]={}) -> str:
|
||||
p.pos["end"] = len(p)
|
||||
content = p[p.pos["start"]:p.pos["end"]]
|
||||
else:
|
||||
error("cmd_include", f"Could not find section {target_section} in file {filename}")
|
||||
error(f"cmd_include: Could not find section {target_section} in file {filename}")
|
||||
except FileNotFoundError:
|
||||
error("cmd_include", f"Could not open file '{filename}'", level=error_levels["serious"], exit_code=exit_codes["FileNotFound"])
|
||||
error(f"cmd_include: Could not open file '{filename}'", level=error_levels["serious"], exit_code=exit_codes["FileNotFound"])
|
||||
content = f"<!-- Could not include '{filename}' -->"
|
||||
if filename.endswith(".md"):
|
||||
try:
|
||||
from markdown import markdown
|
||||
content = markdown(content, output_format="xhtml")
|
||||
except:
|
||||
error("cmd_include", f"Could convert markdown to html for file '{filename}'. Is python-markdown installed?", level=error_levels["critical"], exit_code=exit_codes["MarkdownConversionError"])
|
||||
error(f"cmd_include: Could convert markdown to html for file '{filename}'. Is python-markdown installed?", level=error_levels["critical"], exit_code=exit_codes["MarkdownConversionError"])
|
||||
content = f"<!-- Could not convert to html: '{filename}' -->"
|
||||
glob_dependcies.append(filename)
|
||||
return content
|
||||
@ -388,10 +371,10 @@ def cmd_return(args: str, variables:dict[str, str]={}) -> str:
|
||||
# re_set_map = r"([a-zA-Z0-9_]+)\?\{(([a-zA-Z0-9_]+:.+,)*([a-zA-Z0-9_]+:.+))\}"
|
||||
# <!-- #set section=lang?{*:Fallback,de:Abschnitt,en:Section} -->
|
||||
space = args.find(' ')
|
||||
pdebug("cmd_set", f"varname='{args[:space]}, 'arg='{args[space+1:]}', variables='{variables}'")
|
||||
# pdebug(f"cmd_set: varname='{args[:space]}, 'arg='{args[space+1:]}', variables='{variables}'")
|
||||
if not (space > 0 and space < len(args)-1):
|
||||
variables[args] = ""
|
||||
pdebug("cmd_set", f"Setting to empty string: {args}")
|
||||
pdebug(f"cmd_set: Setting to empty string: {args}")
|
||||
else:
|
||||
varname = args[:space]
|
||||
variables[varname] = ""
|
||||
@ -402,15 +385,15 @@ def cmd_return(args: str, variables:dict[str, str]={}) -> str:
|
||||
match = re.fullmatch(re_set_map_alt, args[space+1:].strip(' '))
|
||||
separator = ';'
|
||||
if match:
|
||||
pdebug("cmd_set", f"Map {match.group()}")
|
||||
pdebug(f"cmd_set: Map {match.group()}")
|
||||
depends = match.groups()[0]
|
||||
if not depends in variables:
|
||||
pdebug("cmd_set", f"Setting from map, but depends='{depends}' is not in variables")
|
||||
pdebug(f"cmd_set: Setting from map, but depends='{depends}' is not in variables")
|
||||
return ""
|
||||
depends_val = variables[depends]
|
||||
for option in match.groups()[1].split(separator):
|
||||
option = option.strip(" ")
|
||||
pdebug("cmd_set", f"Found option {option}")
|
||||
pdebug(f"cmd_set: Found option {option}")
|
||||
colon = option.find(':') # we will find one, regex guarantees
|
||||
if option[:colon].strip(" ") == depends_val or option[:colon].strip(" ") == "*":
|
||||
variables[varname] = option[colon+1:].strip(" ")
|
||||
@ -418,7 +401,7 @@ def cmd_return(args: str, variables:dict[str, str]={}) -> str:
|
||||
else: # simple asignment
|
||||
value = args[space+1:].strip(" ")
|
||||
variables[varname] = value
|
||||
pdebug("cmd_set", f"Assignment {varname} -> {value}")
|
||||
pdebug(f"cmd_set: Assignment {varname} -> {value}")
|
||||
return variables[varname]
|
||||
return ""
|
||||
|
||||
@ -429,7 +412,7 @@ def cmd_set(args: str, variables:dict[str, str]={}) -> str:
|
||||
def cmd_unset(args: str, variables:dict[str, str]={}) -> str:
|
||||
variable = args.strip(' ')
|
||||
if variable not in variables:
|
||||
pdebug("cmd_unset", f"variable '{variable}' is not set", level=error_levels["light"])
|
||||
pdebug(f"unset: variable '{variable}' is not set", level=error_levels["light"])
|
||||
else:
|
||||
variables.pop(variable)
|
||||
return ""
|
||||
@ -447,10 +430,10 @@ def cmd_uncomment(args: str, variables:dict[str, str]={}) -> str:
|
||||
return args
|
||||
|
||||
def cmd_error(args: str, variables:dict[str, str]={}) -> str:
|
||||
error("cmd_error", f"Encounted 'error' command: {args}", level=error_levels["critical"])
|
||||
error(f"Encounted 'error' command: {args}", level=error_levels["critical"])
|
||||
return ""
|
||||
def cmd_warning(args: str, variables:dict[str, str]={}) -> str:
|
||||
error("cmd_warning", f"Encounted 'warning' command: {args}", level=error_levels["light"])
|
||||
error(f"Encounted 'warning' command: {args}", level=error_levels["light"])
|
||||
return ""
|
||||
|
||||
|
||||
@ -474,10 +457,6 @@ command2function:dict[str, Callable[[str, dict[str,str]], str]] = {
|
||||
"""
|
||||
|
||||
class Parser():
|
||||
"""
|
||||
General purpose parser class
|
||||
It has states and positions in a text, which are updated when portions of the text are replaced or removed
|
||||
"""
|
||||
def __init__(self, file):
|
||||
self.file = file
|
||||
self.pos: dict[str, int] = {}
|
||||
@ -488,23 +467,23 @@ class Parser():
|
||||
delete_length = stop - start
|
||||
nl, esl = "\n", "\\n"
|
||||
|
||||
ptrace("Parser.remove", f"Deleting range [{start}, {stop}) of length {delete_length}: '{self.file[start:stop].replace(nl, esl)}'")
|
||||
ptrace(f"- Deleting range [{start}, {stop}) of length {delete_length}: '{self.file[start:stop].replace(nl, esl)}'")
|
||||
assert(stop >= start)
|
||||
assert(stop <= len(self.file))
|
||||
self.file = self.file[:start] + self.file[stop:]
|
||||
for k,pos in self.pos.items():
|
||||
if pos >= stop: self.pos[k] -= delete_length
|
||||
elif pos > start and not k in ignore_bounds: error("Parser.remove", f"Position {k}={pos} within deleted range [{start},{stop})", level=error_levels["light"])
|
||||
elif pos > start and not k in ignore_bounds: error(f"Parser.remove: Position {k}={pos} within deleted range [{start},{stop})", level=1)
|
||||
|
||||
def replace(self, start, stop, replacement, ignore_bounds=[]):
|
||||
def replace(self, start, stop, replacement):
|
||||
assert(stop >= start)
|
||||
assert(stop <= len(self.file))
|
||||
ptrace("Parser.replace", f"Replacing range [{start}, {stop}): '{self.file[start:stop]}' with '{replacement}'")
|
||||
ptrace(f"- Replacing range [{start}, {stop}): '{self.file[start:stop]}' with '{replacement}'")
|
||||
self.file = self.file[:start] + replacement + self.file[stop:]
|
||||
length_difference = stop - start - len(replacement)
|
||||
for k,pos in self.pos.items():
|
||||
if pos >= stop: self.pos[k] -= length_difference
|
||||
elif pos > start and k not in ignore_bounds: error("Parser.replace", f"Position {k}={pos} within replaced range [{start},{stop})", level=error_levels["light"])
|
||||
elif pos > start: error(f"Parser.replace: Position {k}={pos} within replaced range [{start},{stop})", level=1)
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.file[key]
|
||||
@ -532,50 +511,32 @@ class HTMLParser(Parser):
|
||||
self.state["last_condition"] = False # if the last if condition was true
|
||||
self.remove_comments = remove_comments
|
||||
|
||||
def next_line(self):
|
||||
"""update i and line_end"""
|
||||
self.pos["line_end"] = self.file.find('\n', self.i+1)
|
||||
if self.pos["line_end"] < 0: self.pos["line_end"] = len(self)
|
||||
|
||||
def use_variables(self):
|
||||
"""replace variable usages in the current line"""
|
||||
self.replace(self.i, self.pos["line_end"], substitute_variables(self[self.i:self.pos["line_end"]], self.variables))
|
||||
ptrace("HTMLParser.use_variables", f"Line after variable substitution:", self.file[self.i:self.pos["line_end"]])
|
||||
ptrace("> Line after variable substitution:", self.file[self.i:self.pos["line_end"]])
|
||||
|
||||
def add_sidenav_headings(self):
|
||||
"""check if heading for sidenav in line"""
|
||||
match = re.search(re_sidenav_heading, self[self.i:self.pos["line_end"]])
|
||||
if match:
|
||||
Sidenav.addEntry(match.groups()[1], f"#{match.groups()[0]}")
|
||||
ptrace("HTMLParser.add_sidenav_headings:", f"Found heading with id:", match.groups())
|
||||
|
||||
def get_leading_whitespaces(self):
|
||||
"""returns the whitespaces at the start of the line"""
|
||||
# find last newline
|
||||
line_beg = self.file.rfind("\n", 0, self.i)
|
||||
if line_beg < 0: line_beg = 0
|
||||
else: line_beg += 1 # start after newline
|
||||
match = re.match(r"^([ \t]*)", self.file[line_beg:self.pos['line_end']])
|
||||
if not match: return ""
|
||||
else: return match.groups()[0]
|
||||
|
||||
|
||||
# Parsing functions
|
||||
def find_line_end(self):
|
||||
"""
|
||||
line_end -> position of next newline char or EOF
|
||||
"""
|
||||
self.pos["line_end"] = self.file.find('\n', self.i+1)
|
||||
if self.pos["line_end"] < 0: self.pos["line_end"] = len(self)
|
||||
|
||||
ptrace("> Found heading with id:", match.groups())
|
||||
|
||||
def find_comment_begin(self) -> bool:
|
||||
"""
|
||||
find the beginning of a comment in the current line
|
||||
if comment begin was found, jump into the comment, return True
|
||||
cmt_beg -> beginning of COMMENT_BEGIN
|
||||
i -> first character after COMMENT_BEGIN / line_end + 1
|
||||
|
||||
"""
|
||||
# look for comment begin
|
||||
if self.pos["cmt_beg"] < 0: # if not in comment, find next comment
|
||||
self.pos["cmt_beg"] = self.file.find(COMMENT_BEGIN, self.i, self.pos["line_end"])
|
||||
# ptrace(f"i={i}, line_end={line_end}, comment_begin={comment_begin}")
|
||||
if self.pos["cmt_beg"] < 0:
|
||||
self.i = self.pos["line_end"] + 1
|
||||
return False
|
||||
@ -583,51 +544,36 @@ class HTMLParser(Parser):
|
||||
# jump to comment_begin
|
||||
old_i = self.i
|
||||
self.i = self.pos["cmt_beg"] + len(COMMENT_BEGIN) # after comment begin
|
||||
ptrace(f"HTMLParser.find_comment_begin", f"Found comment begin, jumping from pos {old_i} to {self.i}")
|
||||
ptrace(f"> Found comment begin, jumping from pos {old_i} to {self.i}")
|
||||
return True
|
||||
return True # still in previous comment
|
||||
|
||||
|
||||
def find_comment_end(self):
|
||||
"""
|
||||
call after find_comment_begin returns true to update the cmt_end
|
||||
call afterfind_comment_begin returns true to update the cmt_end
|
||||
call continue when returning false
|
||||
cmt_end -> beginning of COMMENT_END / ---
|
||||
cmt_beg -> --- / -1 when invalid comment
|
||||
"""
|
||||
# in comment, i at the character after COMMENT_BEGIN
|
||||
self.pos["cmt_end"] = self.file.find(COMMENT_END, self.i) #, self.pos["line_end"])
|
||||
# sanity checks
|
||||
if self.pos["cmt_end"] < 0:
|
||||
error("HTMLParser.find_comment_end", f"Comment starting in line {pos2line(self.file, self.pos['cmt_beg'])} is never ended.", level=error_levels["serious"])
|
||||
error(f"Comment starting in line {pos2line(self.file, self.pos['cmt_beg'])} is never ended.", level=error_levels["serious"])
|
||||
return False
|
||||
else:
|
||||
tmp_next_begin = self.file.find(COMMENT_BEGIN, self.i)
|
||||
if 0 < tmp_next_begin and tmp_next_begin < self.pos["cmt_end"]:
|
||||
error("HTMLParser.find_comment_end", f"Found next comment begin before the comment starting in line {pos2line(self.file, self.pos['cmt_beg'])} is ended! Skipping comment. Comment without proper closing tags: '{self.file[self.i:self.pos['line_end']]}'", level=error_levels["light"])
|
||||
error(f"Found next comment begin before the comment starting in line {pos2line(self.file, self.pos['cmt_beg'])} is ended! Skipping comment. Comment without proper closing tags: '{self.file[self.i:self.pos['line_end']]}'", level=error_levels["light"])
|
||||
self.pos["cmt_beg"] = -1
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def replace_multiline_comments(self):
|
||||
"""
|
||||
if in a multiline comment, turn every line into a separate comment
|
||||
"""
|
||||
# not a multiline comment
|
||||
if self.pos["line_end"] > self.pos["cmt_end"]: return
|
||||
indent = self.get_leading_whitespaces()
|
||||
self.replace(self.pos["cmt_beg"], self.pos["cmt_end"], self.file[self.pos["cmt_beg"]:self.pos["cmt_end"]].replace("\n", "-->\n" + indent + "<!--"), ignore_bounds=["line_end"])
|
||||
self.find_line_end()
|
||||
self.find_comment_end()
|
||||
|
||||
|
||||
def find_command(self):
|
||||
# either at newline (if in multiline comment) or at comment end
|
||||
self.pos["cmd_beg"] = self.i
|
||||
self.pos["cmd_end"] = min(self.pos["line_end"], self.pos["cmt_end"])
|
||||
assert self.pos["cmd_end"] >= self.i, f"cmd_end={self.pos['cmd_end']}, i={self.i}, line_end={self.pos['line_end']}, cmt_end={self.pos['cmt_end']}"
|
||||
ptrace("HTMLParser.find_command", f"Possible command end: {self.pos['cmd_end']}, possible command: '{self[self.i:self.pos['cmd_end']]}'")
|
||||
ptrace(f"> Possible command end: {self.pos['cmd_end']}, possible command: '{self[self.i:self.pos['cmd_end']]}'")
|
||||
|
||||
# find commands
|
||||
match = re.fullmatch(re_preprocessor_command, self[self.i:self.pos["cmd_end"]].strip(" "))
|
||||
@ -636,10 +582,8 @@ class HTMLParser(Parser):
|
||||
return match
|
||||
|
||||
def replace_command_with_output(self, command_output):
|
||||
# keep indent level
|
||||
indent = self.get_leading_whitespaces()
|
||||
self.replace(self.i, self.pos["cmd_end"], command_output.replace("\n", "\n" + indent))
|
||||
ptrace(f"HTMLParser.replace_command_with_output", f"After command, the line is now '{self.file[self.i:self.pos['line_end']]}'")
|
||||
self.replace(self.i, self.pos["cmd_end"], command_output)
|
||||
ptrace(f"> After insertion, the line is now '{self.file[self.i:self.pos['line_end']]}'")
|
||||
|
||||
def command_end(self):
|
||||
if self.pos["cmd_end"] == self.pos["cmt_end"]: # reached end of comment
|
||||
@ -648,7 +592,7 @@ class HTMLParser(Parser):
|
||||
if self[self.pos["cmt_beg"]-1] == '\n' and self[self.pos["cmt_end"]+len(COMMENT_END)] == '\n': # if the comment consumes the whole line, remove the entire line
|
||||
remove_newline = 1
|
||||
if self.state["cmd_in_cmt"]: # remove comment tags if a command was found
|
||||
ptrace("HTMLParser.command_end", f"Deleting opening comment tags")
|
||||
ptrace(f"Deleting opening comment tags")
|
||||
self.remove(self.pos["cmt_beg"], self.pos["cmt_beg"] + len(COMMENT_BEGIN))
|
||||
self.remove(self.pos["cmt_end"], self.pos["cmt_end"] + len(COMMENT_END) + remove_newline, ignore_bounds=["cmt_end", "cmd_end", "line_end"])
|
||||
# process the line again, because a command might have inserted new comments
|
||||
@ -665,7 +609,7 @@ class HTMLParser(Parser):
|
||||
self.pos["cmt_end"] = -1
|
||||
self.pos["cmd_end"] = -1
|
||||
self.i = self.pos["line_end"] + 1
|
||||
ptrace(f"HTMLParser.command_end", f"Multiline comment, jumping to next line.")
|
||||
ptrace(f"> Multiline comment, jumping to next line.")
|
||||
# i = possible_command_end commented, because if something containing new commands is inserted we need to parse that as well
|
||||
|
||||
|
||||
@ -674,8 +618,8 @@ def parse_file(_file:str, variables:dict[str,str], remove_comments):
|
||||
sidenav_include_pos = -1
|
||||
|
||||
while p.i < len(p): # at start of new line or end of comment
|
||||
p.find_line_end()
|
||||
ptrace("parse_file", f"Processing at i={p.i} in line {pos2line(p.file, p.i)}: '{p[p.i:p.pos['line_end']]}'")
|
||||
p.next_line()
|
||||
ptrace(f"Processing at i={p.i} in line {pos2line(p.file, p.i)}")
|
||||
|
||||
p.use_variables()
|
||||
p.add_sidenav_headings()
|
||||
@ -683,22 +627,21 @@ def parse_file(_file:str, variables:dict[str,str], remove_comments):
|
||||
if not p.find_comment_begin(): continue
|
||||
|
||||
if not p.find_comment_end(): continue
|
||||
p.replace_multiline_comments()
|
||||
|
||||
match = p.find_command()
|
||||
if match:
|
||||
command = match.groups()[0]
|
||||
args = match.groups()[1].replace('\t', ' ').strip(' ')
|
||||
pdebug("parse_file", f"Found command '{command}' with args '{args}'")
|
||||
pdebug(f"> Found command '{command}' with args '{args}'")
|
||||
# delete from previous block if
|
||||
if command in ["elif", "else", "endif"]:
|
||||
if p.pos["conditional_block_beg"] < 0: error("parse_file", f"Misplaced '{command}' in line {pos2line(p.file, p.i)}")
|
||||
if p.pos["conditional_block_beg"] < 0: error(f"Misplaced '{command}' in line {pos2line(p.file, p.i)}")
|
||||
if p.state["last_condition"]:
|
||||
# delete block from here at next endif
|
||||
p.state["last_condition"] = False
|
||||
else:
|
||||
# delete block from last condition statement
|
||||
ptrace("parse_file", f"> Deleting block from last condition")
|
||||
ptrace(f"> Deleting block from last condition")
|
||||
p.remove(p.pos["conditional_block_beg"], p.pos["cmt_beg"])
|
||||
p.i = p.pos["cmd_beg"]
|
||||
p.pos["conditional_block_beg"] = p.i
|
||||
@ -711,14 +654,14 @@ def parse_file(_file:str, variables:dict[str,str], remove_comments):
|
||||
p.pos["conditional_block_beg"] = p.i
|
||||
p.state["last_condition"] = evaluate_condition(args)
|
||||
p.state["any_condition"] = p.state["last_condition"]
|
||||
pdebug("parse_file", f"Command {command} condition evaluated to {p.state['last_condition']}")
|
||||
pdebug(f"> Command {command} condition evaluated to {p.state['last_condition']}")
|
||||
cmd_output = ""
|
||||
elif command =="elif":
|
||||
p.pos["conditional_block_beg"] = p.i
|
||||
p.state["last_condition"] = evaluate_condition(args) if not p.state["any_condition"] else False
|
||||
if p.state["last_condition"]:
|
||||
p.state["any_condition"] = True
|
||||
pdebug("parse_file", f"Command {command} condition evaluated to {p.state['last_condition']}")
|
||||
pdebug(f"> Command {command} condition evaluated to {p.state['last_condition']}")
|
||||
cmd_output = ""
|
||||
elif command == "else":
|
||||
p.pos["conditional_block_beg"] = p.i
|
||||
@ -731,23 +674,18 @@ def parse_file(_file:str, variables:dict[str,str], remove_comments):
|
||||
elif command == "endif":
|
||||
cmd_output = ""
|
||||
elif command not in command2function:
|
||||
error("parse_file", f"Invalid command in line {pos2line(p.file, p.i)}: {command}", level=error_levels["light"])
|
||||
error(f"Invalid command in line {pos2line(p.file, p.i)}: {command}", level=error_levels["light"])
|
||||
cmd_output = ""
|
||||
else:
|
||||
cmd_output = command2function[command](args, variables)
|
||||
else:
|
||||
cmd_output = ""
|
||||
p.replace_command_with_output(cmd_output)
|
||||
else:
|
||||
pdebug("parse_file", f"Did not find command in comment {p.file[p.pos['cmt_beg']:p.pos['cmt_end']+len(COMMENT_END)]}")
|
||||
|
||||
p.command_end()
|
||||
|
||||
if sidenav_include_pos >= 0:
|
||||
p.i = sidenav_include_pos # required before get_leading_whitespaces
|
||||
p.find_line_end() # required before get_leading_whitespaces
|
||||
indent = p.get_leading_whitespaces()
|
||||
return p.file[:sidenav_include_pos] + Sidenav.generate().replace("\n", "\n" + indent) + p.file[sidenav_include_pos:]
|
||||
return p.file[:sidenav_include_pos] + Sidenav.generate() + p.file[sidenav_include_pos:]
|
||||
else:
|
||||
return p.file
|
||||
|
||||
@ -761,11 +699,11 @@ def substitute_variables(html:str, variables:dict[str, str]):
|
||||
matches.append(match)
|
||||
html_list = list(html)
|
||||
for match in reversed(matches):
|
||||
pdebug("substitute_variables", f"Found variable usage {match.groups()[0]}, match from {match.start()} to {match.end()}")
|
||||
pdebug(f"> Found variable usage {match.groups()[0]}, match from {match.start()} to {match.end()}")
|
||||
value = ""
|
||||
if match.groups()[0] in variables: value = variables[match.groups()[0]]
|
||||
else:
|
||||
pdebug("substitute_variables", f"Variable {match.groups()[0]} is used but not defined")
|
||||
pdebug(f"Variable {match.groups()[0]} is used but not defined")
|
||||
for _ in range(match.start(), match.end()):
|
||||
html_list.pop(match.start())
|
||||
html_list.insert(match.start(), value.strip(" "))
|
||||
@ -823,7 +761,7 @@ if __name__ == "__main__":
|
||||
if args.sitemap_remove_ext:
|
||||
current_file_url = os.path.splitext(current_file_url)[0]
|
||||
|
||||
pdebug("main", f"current_file={current_file_url}")
|
||||
pdebug(f"current_file={current_file_url}")
|
||||
|
||||
# sanity checks
|
||||
if not path.isfile(args.input):
|
||||
@ -852,7 +790,7 @@ if __name__ == "__main__":
|
||||
|
||||
output_html = parse_file(target_html, variables, not args.preserve_comments)
|
||||
# remove empty lines
|
||||
output_html = re.sub(r"[\t\r ]*\n(?:[\t\r ]*\n)+", r"\n", output_html)
|
||||
output_html = re.sub(r"[\t\r ]*\n(?:[\t\r ]*\n[\t\r ]*)+", r"\n", output_html)
|
||||
|
||||
# pdebug(f"Output: {output_html}")
|
||||
|
||||
@ -867,7 +805,7 @@ if __name__ == "__main__":
|
||||
if args.output != args.input:
|
||||
glob_dependcies.append(args.input)
|
||||
depfile = generate_dependecy_file(args.output, glob_dependcies)
|
||||
pdebug("main", f"Writing dependency file to {os.path.abspath(args.output_deps)}: {depfile}")
|
||||
pdebug(f"Writing dependency file to {os.path.abspath(args.output_deps)}: {depfile}")
|
||||
with open(args.output_deps, "w") as file:
|
||||
file.write(depfile)
|
||||
if args.sitemap_temp_file:
|
||||
@ -879,6 +817,6 @@ if __name__ == "__main__":
|
||||
with open(args.sitemap_temp_file, "rb") as file:
|
||||
Sitemap.urls = pickle.load(file)
|
||||
sitemap = Sitemap.gen_sidemap()
|
||||
pdebug("main", f"Writing sitemap to {os.path.abspath(args.sitemap_generate)}")
|
||||
pdebug(f"Writing sitemap to {os.path.abspath(args.sitemap_generate)}")
|
||||
with open(args.sitemap_generate, "w") as file:
|
||||
file.write(sitemap)
|
||||
|
Loading…
Reference in New Issue
Block a user