Compare commits

..

No commits in common. "master" and "2021112105" have entirely different histories.

20 changed files with 111 additions and 433 deletions

BIN
.coverage

Binary file not shown.

8
.idea/.gitignore vendored
View File

@ -1,8 +0,0 @@
# 默认忽略的文件
/shelf/
/workspace.xml
# 基于编辑器的 HTTP 客户端请求
/httpRequests/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml

View File

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="C:\Users\Gao42H\miniconda3" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
</module>

View File

@ -1,6 +0,0 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>

View File

@ -1,7 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Black">
<option name="sdkName" value="Python 3.12" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="C:\Users\Gao42H\miniconda3" project-jdk-type="Python SDK" />
</project>

View File

@ -1,8 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/SELab1.iml" filepath="$PROJECT_DIR$/.idea/SELab1.iml" />
</modules>
</component>
</project>

View File

@ -1,6 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="PySciProjectComponent">
<option name="PY_INTERACTIVE_PLOTS_SUGGESTED" value="true" />
</component>
</project>

View File

@ -1,6 +0,0 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="" vcs="Git" />
</component>
</project>

3
.txt
View File

@ -1,3 +0,0 @@
symphony
of
nature

1
1.txt
View File

@ -1 +0,0 @@
The sunlight filtered through the dense canopy, casting intricate patterns on the forest floor. Birds chirped melodiously, creating a symphony of nature finest sounds. Amidst the greenery, a small stream gurgled, its waters crystal clear and refreshing. Suddenly, a deer darted past, startling.To @ explore strange new worlds and worlds and seek strange,To seek out new life and new worlds and new civilizations?

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

192
oop.py
View File

@ -1,26 +1,25 @@
import copy import copy
import heapq import heapq
import re import re
import sys
import time
from math import isinf,inf from math import isinf,inf
import matplotlib.patches
import networkx as nx import networkx as nx
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
from typing import Dict, Generator, List, Optional from typing import Dict, Generator, List, Optional, cast
import random import random
import os
def main(): def main():
# print("Welcome to Lab1") # print("Welcome to Lab1")
print("功能5中输入@停止功能") print("功能5中输入@停止功能")
tu = None tu = None
while True: while True:
i = input("请输入操作q:退出, 0:读入文件, 1:展示图形, 2:查找桥接词, 3:生成新文本, 4:计算最短路径, 5:随机游走):") i = input("请输入操作q:退出, 0:读入文件, 1:展示图形, 2:查找桥接词, 3:生成新文本, 4:计算最短路径, 5:随机游走):")
if i == "q" : if i == "q" :
sys.exit() exit(0)
if i == "0": if i == "0": #shengchengTu
tu=Tu() tu=Tu()
file_name=input("请输入文件名称:") file_name=input("请输入文件名称:")
@ -56,15 +55,15 @@ def main():
print("Invalid input") print("Invalid input")
class Tu : class Tu :
def __init__(self): def __init__(self):
self.dict={} self.dict={}
self.graph=nx.MultiDiGraph() self.graph=nx.MultiDiGraph()
@staticmethod def read_text_file(self,filename):
def read_text_file(filename):
try: try:
with open(filename, 'r', encoding="utf-8") as file: with open(filename, 'r') as file:
text = file.read() text = file.read()
# 用正则表达式将非字母字符替换为空格,并将换行符也替换为空格 # 用正则表达式将非字母字符替换为空格,并将换行符也替换为空格
text = re.sub(r'[^a-zA-Z\n]+', ' ', text) text = re.sub(r'[^a-zA-Z\n]+', ' ', text)
@ -77,7 +76,7 @@ class Tu:
return [] return []
def generate_directed_dict(self,word_sequence): def generate_directed_dict(self,word_sequence):
graph = self.dict graph = self.dict #chunfuzhi,yiqigai
for i in range(len(word_sequence) - 1): for i in range(len(word_sequence) - 1):
current_word = word_sequence[i] current_word = word_sequence[i]
next_word = word_sequence[i + 1] next_word = word_sequence[i + 1]
@ -110,10 +109,9 @@ class Tu:
def draw_directed_graph(self): def draw_directed_graph(self):
G=self.graph G=self.graph
pos = nx.spring_layout(G) pos = nx.spring_layout(G)
plt.rcParams['figure.figsize'] = (12.8, 7.2)
nx.draw_networkx(G, pos, with_labels=True, node_size=1000, nx.draw_networkx(G, pos, with_labels=True, node_size=1000, node_color="skyblue",edge_color="black", font_size=10, font_weight="bold",
node_color="skyblue", edge_color="black", font_size=10, arrows=True, connectionstyle='arc3,rad=0.2')
font_weight="bold", arrows=True, connectionstyle='arc3,rad=0.2')
edge_labels = nx.get_edge_attributes(G, 'weight') edge_labels = nx.get_edge_attributes(G, 'weight')
# 调整箭头位置 # 调整箭头位置
for edge, weight in edge_labels.items(): for edge, weight in edge_labels.items():
@ -121,11 +119,9 @@ class Tu:
dx = pos[edge[0]][0] - pos[edge[1]][0] dx = pos[edge[0]][0] - pos[edge[1]][0]
dy = pos[edge[0]][1] - pos[edge[1]][1] dy = pos[edge[0]][1] - pos[edge[1]][1]
plt.annotate(weight, ( plt.annotate(weight, (
(pos[edge[0]][0] + pos[edge[1]][0]) / 2 + dy * 0.1, (pos[edge[0]][0] + pos[edge[1]][0]) / 2 + dy * 0.1, (pos[edge[0]][1] + pos[edge[1]][1]) / 2 - dx * 0.1))
(pos[edge[0]][1] + pos[edge[1]][1]) / 2 - dx * 0.1))
else: # 反向边不存在 else: # 反向边不存在
plt.annotate(weight, ((pos[edge[0]][0] + pos[edge[1]][0]) / 2, plt.annotate(weight, ((pos[edge[0]][0] + pos[edge[1]][0]) / 2, (pos[edge[0]][1] + pos[edge[1]][1]) / 2))
(pos[edge[0]][1] + pos[edge[1]][1]) / 2))
plt.show() plt.show()
def drawDirectedGraph(self): def drawDirectedGraph(self):
@ -138,15 +134,27 @@ class Tu:
print("No", word1, "or", word2, "in the graph!") print("No", word1, "or", word2, "in the graph!")
return [] return []
bridge_words = [ bridge_words = []
word for word in graph[word1] bridge_words_origin = []
if word2 in graph.get(word, {}) for bridge_word in graph:
] if word1 == bridge_word:
bridge_words = list(graph[bridge_word].keys())
bridge_words_origin = copy.deepcopy(bridge_words)
for wordi in bridge_words_origin:
if graph.get(wordi) != None:
if word2 not in graph[wordi].keys():
bridge_words.remove(wordi)
else:
bridge_words.remove(wordi)
return bridge_words return bridge_words
@staticmethod def print_bridge_words(self,bridge_words,word1,word2):
def print_bridge_words(bridge_words, word1, word2):
if not bridge_words: if not bridge_words:
print("No bridge words from", word1, "to", word2, "!") print("No bridge words from", word1, "to", word2, "!")
@ -161,11 +169,7 @@ class Tu:
word1 = self.input_check(word1) word1 = self.input_check(word1)
word2 = self.input_check(word2) word2 = self.input_check(word2)
bridge_words = self.find_bridge_words(word1, word2) bridge_words = self.find_bridge_words(word1, word2)
if bridge_words:
self.print_bridge_words(bridge_words,word1,word2) self.print_bridge_words(bridge_words,word1,word2)
return bridge_words
else:
return bridge_words
def insert_bridge_words(self, text): def insert_bridge_words(self, text):
@ -198,42 +202,24 @@ class Tu:
print("There are upper characters in your input") print("There are upper characters in your input")
print(self.insert_bridge_words(text_re)) print(self.insert_bridge_words(text_re))
def find_shortest_path_old(self, word1, word2): def find_shortest_path(self,word1, word2):
graph=self.graph graph=self.graph
try: try:
shortest_path_generator = ( shortest_path_generator = nx.all_shortest_paths(graph, source=word1, target=word2, weight='weight')
nx.all_shortest_paths(graph, source=word1, target=word2, weight='weight')) shortest_length = nx.shortest_path_length(graph, source=word1, target=word2, weight='weight')
shortest_length = ( return shortest_path_generator, shortest_length
nx.shortest_path_length(graph, source=word1, target=word2, weight='weight')) except nx.NetworkXNoPath:
return None, None
def find_shortest_path_re(self,word1, word2):
graph=self.graph
try:
shortest_path_generator = self.all_simple_paths_graph(word1, word2)
shortest_length=self.calc_shortest_path_len(word1,word2)
return shortest_path_generator, shortest_length return shortest_path_generator, shortest_length
except nx.NetworkXNoPath: except nx.NetworkXNoPath:
return None, None return None, None
def find_shortest_path(self, word1, word2):
try:
(shortest_path_list, shortest_length) = self.calc_shortest_path_len(word1, word2)
return shortest_path_list, shortest_length
except nx.NetworkXNoPath:
return None, None
def find_shortest_path_ex(self, word1, word2):
try:
shortest_path_generator = self.all_simple_paths_graph(word1, word2)
shortest_length = self.calc_shortest_path_len(word1, word2)
shortest_path_list = []
for shortest_path in shortest_path_generator:
if shortest_path.__len__() == shortest_length:
shortest_path_list.append(shortest_path)
return shortest_path_list, shortest_length
except nx.NetworkXNoPath:
return None, None
def draw_shortest_path(self, shortest_path_list): def draw_shortest_path(self, shortest_path_list):
graph=self.graph graph=self.graph
@ -241,6 +227,7 @@ class Tu:
# !!! HUATU ROLL YANSE # !!! HUATU ROLL YANSE
pos = nx.spring_layout(graph) pos = nx.spring_layout(graph)
nx.draw_networkx_nodes(graph, pos, node_size=1000, node_color="skyblue") nx.draw_networkx_nodes(graph, pos, node_size=1000, node_color="skyblue")
nx.draw_networkx_labels(graph, pos, font_size=10, font_weight="bold") nx.draw_networkx_labels(graph, pos, font_size=10, font_weight="bold")
@ -255,57 +242,39 @@ class Tu:
#print(shortest_path) #print(shortest_path)
if (edge in zip(shortest_path[:-1], shortest_path[1:]) or if edge in zip(shortest_path[:-1], shortest_path[1:]) or edge in zip(shortest_path[1:], shortest_path[:-1]):
edge in zip(shortest_path[1:], shortest_path[:-1])):
nx.draw_networkx_edges(graph, pos, edgelist=[edge], width=2.0, edge_color=num,
arrows=True, arrowstyle="->", arrowsize=30,
connectionstyle='arc3,rad=0.2')
nx.draw_networkx_edges(graph, pos, edgelist=[edge], width=2.0, edge_color=num, arrows=True,arrowstyle="->",arrowsize=30
,connectionstyle='arc3,rad=0.2')
else: else:
nx.draw_networkx_edges(graph, pos, edgelist=[edge], width=1.0, nx.draw_networkx_edges(graph, pos, edgelist=[edge], width=1.0, edge_color="black", arrows=True,arrowstyle="->",arrowsize=30
edge_color="black", ,connectionstyle='arc3,rad=0.2')
arrows=True, arrowstyle="->", arrowsize=30,
connectionstyle='arc3,rad=0.2')
plt.show() plt.show()
time.sleep(1)
def calcShortestPath(self,word1, word2): def calcShortestPath(self,word1, word2):
if word2 == "": if word2 == "":
word1 = self.input_check(word1) word1 = self.input_check(word1)
if word1 not in self.graph :
print("No", word1, "or", word2, "in the graph!")
return [], 0
for wordtmp in self.dict : for wordtmp in self.dict :
if wordtmp == word1 : if wordtmp == word1 :
continue continue
else: else:
result=self.calc_shortest_path(word1, wordtmp) self.calc_shortest_path(word1,wordtmp)
if result == []:
print("No path exists between", word1, "and", word2)
else:
print(result)
pass pass
else: else:
if word1 not in self.graph or word2 not in self.graph:
print("No", word1, "or", word2, "in the graph!")
return [], 0
word1 = self.input_check(word1) word1 = self.input_check(word1)
word2 = self.input_check(word2) word2 = self.input_check(word2)
result = self.calc_shortest_path(word1, word2) self.calc_shortest_path(word1,word2)
pass pass
if result==[] :
print("No path exists between", word1, "and", word2)
else:
print(result)
result_len = 0 if result==[] or result is None else len(result[0])-1
return result,result_len
def calc_shortest_path_old(self, word1, word2):
shortest_path_generator, shortest_length = self.find_shortest_path_old(word1, word2) def calc_shortest_path(self,word1, word2):
shortest_path_generator, shortest_length = self.find_shortest_path_re(word1, word2)
shortest_path_list=[] shortest_path_list=[]
for shortest_path in shortest_path_generator: for shortest_path in shortest_path_generator:
@ -316,28 +285,8 @@ class Tu:
shortest_path_list.append(shortest_path) shortest_path_list.append(shortest_path)
if shortest_path_list.__len__()>0: if shortest_path_list.__len__()>0:
self.draw_shortest_path(shortest_path_list) self.draw_shortest_path(shortest_path_list)
return shortest_path_list
else: else:
return [] print("No path exists between", word1, "and", word2)
#print("No path exists between", word1, "and", word2)
def calc_shortest_path(self, word1, word2):
shortest_path_list, shortest_length = self.find_shortest_path_ex(word1, word2)
for shortest_path in shortest_path_list:
if shortest_path:
print("Shortest path:", ''.join(shortest_path))
print("Length of shortest path:", shortest_length)
if shortest_path_list.__len__() > 0:
self.draw_shortest_path(shortest_path_list)
return shortest_path_list
else:
return []
#print("No path exists between", word1, "and", word2)
def random_traversal(self): def random_traversal(self):
@ -345,6 +294,7 @@ class Tu:
filename = input("Enter the filename to save traversal results: ") filename = input("Enter the filename to save traversal results: ")
filename+=".txt" filename+=".txt"
graph=copy.deepcopy(self.dict) graph=copy.deepcopy(self.dict)
start_node = random.choice(list(graph.keys())) start_node = random.choice(list(graph.keys()))
visited_nodes = set() visited_nodes = set()
@ -359,7 +309,7 @@ class Tu:
if input()=="@": if input()=="@":
file.close() file.close()
break break
if graph.get(current_node) is not None: if graph.get(current_node) != None:
pass pass
else: else:
break break
@ -379,10 +329,11 @@ class Tu:
def randomWalk(self): def randomWalk(self):
self.random_traversal() self.random_traversal()
@staticmethod
def input_check(input_word): def input_check(self, input_word):
(input_word_re,input_word_ren)=re.subn(r'[^a-zA-Z\n]', ' ', input_word) (input_word_re,input_word_ren)=re.subn(r'[^a-zA-Z\n]', ' ', input_word)
if input_word_ren>0 : if input_word_ren>0 :
print("There are illegal signs in your input,the amount is "+str(input_word_ren)) print("There are illegal signs in your input,the amount is "+str(input_word_ren))
@ -394,6 +345,7 @@ class Tu:
return tmp[0] return tmp[0]
def all_simple_paths_graph(self, source: str, targets: str) -> Generator[List[str], None, None]: def all_simple_paths_graph(self, source: str, targets: str) -> Generator[List[str], None, None]:
G = self.graph G = self.graph
cutoff = len(G) - 1 # 设置路径的最大深度,防止无限循环。 cutoff = len(G) - 1 # 设置路径的最大深度,防止无限循环。
@ -422,15 +374,13 @@ class Tu:
stack.pop() stack.pop()
visited.popitem() visited.popitem()
def calc_shortest_path_len(self, word1: str, word2: str) -> int: def calc_shortest_path_len(self, word1: str, word2: str) -> str:
if word1 not in self.graph.nodes or word2 not in self.graph.nodes: if word1 not in self.graph.nodes or word2 not in self.graph.nodes:
return 0 return ""
distances = {node: inf for node in self.graph.nodes} distances = {node: inf for node in self.graph.nodes} # 存储word1到所有结点的距离初始化为无穷大
# 存储word1到所有结点的距离初始化为无穷大 previous_nodes: Dict[str, Optional[str]] = {node: None for node in self.graph.nodes} # 存储每个节点最短路径中的前一个节点初始化为None
previous_nodes: Dict[str, Optional[str]] = {node: None for node in
self.graph.nodes} # 存储每个节点最短路径中的前一个节点初始化为None
distances[word1] = 0 # 距离初始化为0 distances[word1] = 0 # 距离初始化为0
priority_queue = [(0, word1)] # 优先级队列,用于按照从小到大获取节点 priority_queue = [(0, word1)] # 优先级队列,用于按照从小到大获取节点
@ -462,9 +412,9 @@ class Tu:
path.insert(0, current_node) path.insert(0, current_node)
if isinf(distances[word2]): # 目标节点不可达 if isinf(distances[word2]): # 目标节点不可达
return 0 return ""
return path.__len__() return path.__len__()
# return (' '.join(path),path.__len__()) return ' '.join(path)
if __name__ == '__main__': if __name__ == '__main__':

3
t1.txt
View File

@ -1,3 +0,0 @@
small
stream
gurgled

28
t2.txt
View File

@ -1,28 +0,0 @@
melodiously
creating
a
small
stream
gurgled
its
waters
crystal
clear
and
refreshing
suddenly
a
deer
darted
past
startling
to
seek
out
new
worlds
and
new
life
and
worlds

34
t3.txt
View File

@ -1,34 +0,0 @@
and
seek
out
new
life
and
refreshing
suddenly
a
symphony
of
nature
finest
sounds
amidst
the
forest
floor
birds
chirped
melodiously
creating
a
deer
darted
past
startling
to
explore
strange
new
worlds
and
worlds

24
t4.txt
View File

@ -1,24 +0,0 @@
nature
finest
sounds
amidst
the
greenery
a
deer
darted
past
startling
to
seek
strange
new
life
and
seek
out
new
worlds
and
new
civilizations

130
test.py
View File

@ -1,130 +0,0 @@
import unittest
from oop import Tu
class TextProcessor(Tu):
def __init__(self):
super().__init__()
class TestQueryBridgeWords(unittest.TestCase):
def setUp(self):
# Initialize a graph for testing
self.graph = {
'a': {'b': 1, 'c': 2},
'b': {'c': 1, 'd': 2},
'c': {'d': 1},
'x': {},
'z': {}
}
self.processor = TextProcessor()
self.processor.generate_directed_dict(self.processor.read_text_file("1.txt"))
self.processor.generate_directed_graph()
def test_normal_path1(self):
# 正常情况:存在路径
word1 = 'to'
word2 = 'out'
expected_path = ['to', 'seek', 'out']
expected_length = 2
path,length = self.processor.calcShortestPath(word1, word2)
self.assertEqual(path, [expected_path])
self.assertEqual(length, expected_length)
"""def test_normal_path2(self):
# 正常情况:存在路径
word1 = 'to'
word2 = 'new'
expected_path = ['to', 'seek', 'out',"new"],['to', 'seek', "strange",'new'],['to', 'explore', "strange",'new']
expected_length = 3
path, length = self.processor.calcShortestPath(word1, word2)
path_set=set([])
for i in path :
path_set.add(i)
self.assertSetEqual(path_set, set(expected_path))
self.assertEqual(length, expected_length)"""
def test_no_path(self):
# 无路径情况
word1 = 'civilizations'
word2 = 'to'
expected_path = []
expected_length = 0
path, length = self.processor.calcShortestPath(word1, word2)
self.assertEqual(path, expected_path)
self.assertEqual(length, expected_length)
def test_node_not_exists(self):
# 节点不存在情况
word1 = 'now'
word2 = 'lod'
expected_path = []
expected_length = 0
path, length = self.processor.calcShortestPath(word1, word2)
self.assertEqual(path, expected_path)
self.assertEqual(length, expected_length)
def test_same_node(self):
# 同一节点情况
word1 = 'to'
word2 = 'to'
expected_path = []
expected_length = 0
path, length = self.processor.calcShortestPath(word1, word2)
self.assertEqual(path, expected_path)
self.assertEqual(length, expected_length)
def test_valid_bridge_words_exist(self):
# Valid equivalence class: bridge words exist
result = self.processor.queryBridgeWords('the', 'floor')
self.assertIn('forest', result)
def test_valid_bridge_words_not_exist(self):
# Valid equivalence class: no bridge words
result = self.processor.queryBridgeWords('on', 'the')
self.assertEqual(result, [])
def test_invalid_word1_not_in_graph(self):
# Invalid equivalence class: word1 not in graph
result = self.processor.queryBridgeWords('an', 'a')
self.assertEqual(result, [])
def test_invalid_word2_not_in_graph(self):
# Invalid equivalence class: word2 not in graph
result = self.processor.queryBridgeWords('a', 'an')
self.assertEqual(result, [])
def test_invalid_both_words_not_in_graph(self):
# Invalid equivalence class: both words not in graph
result = self.processor.queryBridgeWords('now', 'lod')
self.assertEqual(result, [])
def test_edge_case_min_word(self):
# Edge case: minimum word
result = self.processor.queryBridgeWords('a', 'b')
self.assertEqual(result, [])
def test_edge_case_max_word(self):
# Edge case: maximum word
result = self.processor.queryBridgeWords('x', 'z')
self.assertEqual(result, [])
def test_edge_case_no_bridge_words(self):
# Edge case: no bridge words
result = self.processor.queryBridgeWords('new', 'worlds')
self.assertEqual(result, [])
def test_edge_case_single_bridge_word(self):
# Edge case: single bridge word
result = self.processor.queryBridgeWords('the', 'floor')
self.assertIn('forest', result)
if __name__ == '__main__':
unittest.main()