algorithm/hello-algo
1
0
Fork 0
mirror of https://github.com/krahets/hello-algo.git synced 2025-07-24 02:03:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

1. Add build script for Java.

Browse Source 
2. Add height limitation for code blocks in extra.css.
3. Fix "节点" to "结点".
This commit is contained in:
krahets
2023-02-07 04:43:52 +08:00
parent b14568151c
commit ecbf2d1560
54 changed files with 457 additions and 1633 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
docs/utils/build_markdown.py
View File

@ -11,6 +11,8 @@ import re
import glob
import shutil
from docs.utils.extract_code_python import ExtractCodeBlocksPython
from docs.utils.extract_code_java import ExtractCodeBlocksJava
def build_markdown(md_path):
with open(md_path, "r") as f:
@ -19,6 +21,7 @@ def build_markdown(md_path):
code_blocks_dict = {}
file_pattern = re.compile(r'\s*```(\w+)\s+title="(.+)"')
src_pattern = re.compile(r'\s*\[class\]\{(.*?)\}-\[func\]\{(.*?)\}')
for i in range(len(lines)):
# Find the line target to the source codes
src_match = src_pattern.match(lines[i])
@ -28,48 +31,43 @@ def build_markdown(md_path):
file_match = file_pattern.match(lines[j])
if file_match is not None:
break
# Get code blocks
# Get the coresponding language code extractor
lang = file_match[1]
file_name = file_match[2]
extractor = extractor_dict[lang]
# Get code blocks
if file_name not in code_blocks_dict:
code_blocks_dict[file_name] = ExtractCodeBlocksPython(
code_blocks_dict[file_name] = extractor.extract(
file_path=osp.dirname(md_path).replace("docs/", f"codes/{lang}/") + f"/{file_name}")
header_line = i
class_label = src_match[1]
class_label = src_match[1]
func_label = src_match[2]
code_blocks = code_blocks_dict[file_name]
src_info = {
"line_number": i,
"class_label": src_match[1],
"func_label": src_match[2],
"code_blocks": code_blocks_dict[file_name]
}
# Add the class to the doc
if not func_label and class_label:
if class_label in code_blocks.classes:
if class_label in code_blocks["classes"]:
lines.pop(header_line)
class_block = code_blocks.classes[class_label]["block"]
class_block = code_blocks["classes"][class_label]["block"]
for code_line in class_block[::-1]:
ind = " " * 4 if code_line != "\n" else ""
lines.insert(header_line, ind + code_line)
# Add the function to the doc
elif func_label and not class_label:
if func_label in code_blocks.functions:
if func_label in code_blocks["funcs"]:
lines.pop(header_line)
func_block = code_blocks.functions[func_label]
func_block = code_blocks["funcs"][func_label]
for code_line in func_block["block"][::-1]:
ind = " " * 4 if code_line != "\n" else ""
lines.insert(header_line, ind + code_line)
# Add the class method to the doc
elif func_label and class_label:
if class_label in code_blocks.classes:
class_dict = code_blocks.classes[class_label]
if func_label in class_dict["functions"]:
if class_label in code_blocks["classes"]:
class_dict = code_blocks["classes"][class_label]
if func_label in class_dict["funcs"]:
lines.pop(header_line)
func_block = class_dict["functions"][func_label]
func_block = class_dict["funcs"][func_label]
for code_line in func_block["block"][::-1]:
lines.insert(header_line, code_line)
@ -78,10 +76,17 @@ def build_markdown(md_path):
print(f"Built {md_path}")
extractor_dict = {
"java": ExtractCodeBlocksJava(),
"python": ExtractCodeBlocksPython(),
}
if __name__ == "__main__":
# Copy files to the build dir
shutil.copytree("docs", "build", dirs_exist_ok=True)
shutil.rmtree("build/utils")
# Build docs
for md_path in glob.glob("docs/chapter_*/*.md"):
for md_path in glob.glob("docs/chapter_*/*.md"):
build_markdown(md_path)

145
docs/utils/extract_code_java.py Normal file
View File

@ -0,0 +1,145 @@
"""
File: extract_code_python.py
Created Time: 2023-02-07
Author: Krahets (krahets@163.com)
"""
import re
import os
import os.path as osp
class ExtractCodeBlocksJava:
def __init__(self) -> None:
self.langs = ["java"]
# Pattern to match function names and class names
self.func_pattern = r'(\s+)(public|private|)\s*(static|)\s*(\S+)\s+(\w+)(\(.*\))\s+\{'
self.class_pattern = r'(public|)\s*class\s+(\w+)\s*\{'
# Pattern to match the start and end of a block
self.block_end_pattern = '^\s{ind}\}'
self.block_start_pattern = '^\s{ind}\/\*.+\*\/'
def extract(self, file_path):
self.file_path = file_path
with open(file_path) as f:
self.lines = f.readlines()
self.content = "".join(self.lines)
# Detect and extract all the classes along with its fucntions
classes = self.extract_class_blocks()
# Remove 'static'
self.post_process(classes)
return {
"classes": classes
}
def post_process(self, classes):
for clas in classes.values():
funcs = clas["funcs"]
for func in funcs.values():
for i, line in enumerate(func["block"]):
if "static " in line:
func["block"][i] = line.replace("static ", "")
break
def search_block(self, header_line, indentation):
"""
Search class/function block given the header_line and indentation
"""
start_line, end_line = 0, len(self.lines)
block_end_pattern = re.compile(self.block_end_pattern.replace("ind", str(indentation)))
block_start_pattern = re.compile(self.block_start_pattern.replace("ind", str(indentation)))
# Search the code
for i in range(header_line + 1, len(self.lines)):
if re.match(block_end_pattern, self.lines[i]) is not None:
end_line = i
break
# Search the header comment
for i in range(header_line - 1, -1, -1):
if re.search(block_start_pattern, self.lines[i]) is not None:
start_line = i
break
code_block = self.lines[start_line:end_line + 1]
# Remove empty lines at bottom
for i in range(len(code_block) - 1, -1, -1):
if re.search("^\s*\n", code_block[i]) is None:
break
end_line -= 1
return start_line, end_line, self.lines[start_line:end_line + 1]
def extract_function_blocks(self, indentation=4, start_line=-1, end_line=-1):
"""
Extract all the functions with given indentation
"""
funcs = {}
if start_line == -1:
start_line = 0
if end_line == -1:
end_line = len(self.lines) - 1
func_pattern = re.compile(self.func_pattern)
for line_num in range(start_line, end_line + 1):
# Search the function header
func_match = func_pattern.match(self.lines[line_num])
if func_match is None: continue
# The function should match the input indentation
if len(func_match.group(1)) != indentation: continue
header_line = line_num
# Search the block from the header line
start_line, end_line, func_block = self.search_block(header_line, indentation)
# Construct the funcs dict
func_label = func_match.group(5)
funcs[func_label] = {
"indentation": indentation,
"line_number": {
"start": start_line,
"end": end_line,
"header": header_line,
},
"block": func_block,
}
return funcs
def extract_class_blocks(self):
"""
Extract all the classes with given indentation
"""
classes = {}
class_pattern = re.compile(self.class_pattern)
for line_num, line in enumerate(self.lines):
# Search the class header
class_match = class_pattern.match(line)
if class_match is None: continue
header_line = line_num
# Search the block from the header line
start_line, end_line, class_block = self.search_block(header_line, 0)
# Construct the classes dict
class_label = class_match.group(2)
classes[class_label] = {
"indentation": 0,
"line_number": {
"start": start_line,
"end": end_line,
"header": header_line,
},
"block": class_block,
"funcs": self.extract_function_blocks(
indentation=4, start_line=start_line, end_line=end_line)
}
return classes
# ext = ExtractCodeBlocksJava()
# ext.extract("codes/java/chapter_array_and_linkedlist/array.java")
# ext.extract("codes/java/chapter_array_and_linkedlist/my_list.java")

57
docs/utils/extract_code_python.py
View File

@ -1,44 +1,55 @@
"""
File: extract_code_python.py
Created Time: 2023-02-06
Created Time: 2023-02-07
Author: Krahets (krahets@163.com)
"""
import re
import os
import os.path as osp
import glob
class ExtractCodeBlocksPython:
def __init__(self, file_path) -> None:
def __init__(self) -> None:
self.langs = ["python"]
# Pattern to match function names and class names
self.func_pattern = r'(\s*)def\s+(\w+)\s*\('
self.class_pattern = r'class\s+(\w+)'
# Pattern to match the start and end of a block
self.block_end_pattern = '^\s{0,ind}\S+.*\n'
self.block_start_pattern = '^\s{ind}""".+'
def extract(self, file_path):
self.file_path = file_path
with open(file_path) as f:
self.lines = f.readlines()
self.content = "".join(self.lines)
# Regular expression pattern to match function names and class names
self.func_pattern = re.compile(r'(\s*)def\s+(\w+)\s*\(')
self.class_pattern = re.compile(r'class\s+(\w+)')
# Detect and extract all the classes and fucntions
self.classes = self.extract_class_blocks()
self.functions = self.extract_function_blocks()
classes = self.extract_class_blocks()
funcs = self.extract_function_blocks()
return {
"classes": classes,
"funcs": funcs,
}
def search_block(self, header_line, indentation):
"""
Search class/function block given the header_line and indentation
"""
start_line, end_line = 0, len(self.lines)
block_end_pattern = re.compile(self.block_end_pattern.replace("ind", str(indentation)))
block_start_pattern = re.compile(self.block_start_pattern.replace("ind", str(indentation)))
# Search the code
for i in range(header_line + 1, len(self.lines)):
if re.search("^\s*\n|^\s{ind}\s+.+\n".replace("ind", str(indentation)),
self.lines[i]) is None:
if re.match(block_end_pattern, self.lines[i]) is not None:
end_line = i
break
# Search the header comment
for i in range(header_line - 1, -1, -1):
if re.search('^\s{ind}""".+'.replace("ind", str(indentation)),
self.lines[i]) is not None:
if re.search(block_start_pattern, self.lines[i]) is not None:
start_line = i
break
func_block = self.lines[start_line:end_line]
@ -55,16 +66,18 @@ class ExtractCodeBlocksPython:
"""
Extract all the functions with given indentation
"""
functions = {}
funcs = {}
if start_line == -1:
start_line = 0
if end_line == -1:
end_line = len(self.lines) - 1
func_pattern = re.compile(self.func_pattern)
for line_num in range(start_line, end_line + 1):
# Search the function header
func_match = self.func_pattern.match(self.lines[line_num])
func_match = func_pattern.match(self.lines[line_num])
if func_match is None: continue
# The function should match the input indentation
if len(func_match.group(1)) != indentation: continue
@ -72,9 +85,9 @@ class ExtractCodeBlocksPython:
# Search the block from the header line
start_line, end_line, func_block = self.search_block(header_line, indentation)
# Construct the functions dict
# Construct the funcs dict
func_label = func_match.group(2)
functions[func_label] = {
funcs[func_label] = {
"indentation": indentation,
"line_number": {
"start": start_line,
@ -84,7 +97,7 @@ class ExtractCodeBlocksPython:
"block": func_block,
}
return functions
return funcs
def extract_class_blocks(self):
"""
@ -92,9 +105,11 @@ class ExtractCodeBlocksPython:
"""
classes = {}
class_pattern = re.compile(self.class_pattern)
for line_num, line in enumerate(self.lines):
# Search the class header
class_match = self.class_pattern.match(line)
class_match = class_pattern.match(line)
if class_match is None: continue
header_line = line_num
@ -110,7 +125,7 @@ class ExtractCodeBlocksPython:
"header": header_line,
},
"block": class_block,
"functions": self.extract_function_blocks(
"funcs": self.extract_function_blocks(
indentation=4, start_line=start_line, end_line=end_line)
}