Public-Mirror/LunaTranslator
1
0
Fork 0
mirror of https://github.com/HIllya51/LunaTranslator.git synced 2024-12-29 16:44:13 +08:00
Code Issues Projects Releases Wiki Activity

amb

Browse Source
This commit is contained in:
恍兮惚兮 2024-05-22 02:50:11 +08:00
parent bef522ec0c
commit fe71aab2b3
2 changed files with 78 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

143
LunaTranslator/LunaTranslator/cishu/mdict.py
View File

@ -2340,24 +2340,17 @@ class mdict(cishubase):
print_exc() print_exc()
def querycomplex(self, word, index): def querycomplex(self, word, index):
# 0 严格，1 前缀，2 后缀，3 中缀
results = [] results = []
results += index(word) diss = {}
if self.config["ambiguity"] == 0: import winsharedutils
_ = []
for __ in results: for k in index("*" + word + "*"):
if __.lower() == word: dis = winsharedutils.distance(k, word)
_.append(__) if dis <= self.config["ambiguity"]:
results = _ results.append(k)
if self.config["ambiguity"] >= 2: diss[k] = dis
for k in index("*" + word):
if k not in results: return sorted(results, key=lambda x: diss[x])
results.append(k)
if self.config["ambiguity"] >= 3:
for k in index("*" + word + "*"):
if k not in results:
results.append(k)
return results
def parse_strings(self, input_string): def parse_strings(self, input_string):
parsed_strings = [] parsed_strings = []
@ -2462,77 +2455,95 @@ class mdict(cishubase):
html += htmlitem html += htmlitem
# print(html) # print(html)
return html return html
def get_mime_type_from_magic(self,magic_bytes):
if magic_bytes.startswith(b'OggS'): def get_mime_type_from_magic(self, magic_bytes):
return 'audio/ogg' if magic_bytes.startswith(b"OggS"):
elif magic_bytes.startswith(b'\x1A\x45\xDF\xA3'): # EBML header (Matroska) return "audio/ogg"
return 'video/webm' elif magic_bytes.startswith(b"\x1A\x45\xDF\xA3"): # EBML header (Matroska)
elif magic_bytes.startswith(b'\x52\x49\x46\x46') and magic_bytes[8:12] == b'WEBP': return "video/webm"
return 'image/webp' elif (
elif magic_bytes.startswith(b'\xFF\xD8\xFF'): magic_bytes.startswith(b"\x52\x49\x46\x46") and magic_bytes[8:12] == b"WEBP"
return 'image/jpeg' ):
elif magic_bytes.startswith(b'\x89\x50\x4E\x47\x0D\x0A\x1A\x0A'): return "image/webp"
return 'image/png' elif magic_bytes.startswith(b"\xFF\xD8\xFF"):
elif magic_bytes.startswith(b'GIF87a') or magic_bytes.startswith(b'GIF89a'): return "image/jpeg"
return 'image/gif' elif magic_bytes.startswith(b"\x89\x50\x4E\x47\x0D\x0A\x1A\x0A"):
elif magic_bytes.startswith(b'\x00\x00\x01\xBA') or magic_bytes.startswith(b'\x00\x00\x01\xB3'): return "image/png"
return 'video/mpeg' elif magic_bytes.startswith(b"GIF87a") or magic_bytes.startswith(b"GIF89a"):
elif magic_bytes.startswith(b'\x49\x44\x33') or magic_bytes.startswith(b'\xFF\xFB'): return "image/gif"
return 'audio/mpeg' elif magic_bytes.startswith(b"\x00\x00\x01\xBA") or magic_bytes.startswith(
b"\x00\x00\x01\xB3"
):
return "video/mpeg"
elif magic_bytes.startswith(b"\x49\x44\x33") or magic_bytes.startswith(
b"\xFF\xFB"
):
return "audio/mpeg"
else: else:
return 'application/octet-stream' return "application/octet-stream"
def repairtarget(self,index,base,html_content):
def repairtarget(self, index, base, html_content):
import base64 import base64
src_pattern = r'src="([^"]+)"' src_pattern = r'src="([^"]+)"'
href_pattern = r'href="([^"]+)"' href_pattern = r'href="([^"]+)"'
src_matches = re.findall(src_pattern, html_content) src_matches = re.findall(src_pattern, html_content)
href_matches = re.findall(href_pattern, html_content) href_matches = re.findall(href_pattern, html_content)
for url in src_matches + href_matches: for url in src_matches + href_matches:
oked=False oked = False
try: try:
try: try:
with open(os.path.join(base, url), 'rb') as f: with open(os.path.join(base, url), "rb") as f:
file_content = f.read() file_content = f.read()
except: except:
url1=url.replace('/','\\') url1 = url.replace("/", "\\")
if not url1.startswith('\\'): if not url1.startswith("\\"):
url1='\\'+url1 url1 = "\\" + url1
try: try:
file_content=index.mdd_lookup(url1)[0] file_content = index.mdd_lookup(url1)[0]
except: except:
func=url.split(r'://')[0] func = url.split(r"://")[0]
url1=url.split(r'://')[1] url1 = url.split(r"://")[1]
url1=url1.replace('/','\\') url1 = url1.replace("/", "\\")
if not url1.startswith('\\'): if not url1.startswith("\\"):
url1='\\'+url1 url1 = "\\" + url1
file_content=index.mdd_lookup(url1)[0] file_content = index.mdd_lookup(url1)[0]
if func=='sound': if func == "sound":
base64_content = base64.b64encode(file_content).decode('utf-8') base64_content = base64.b64encode(file_content).decode(
"utf-8"
)
import uuid import uuid
uid=str(uuid.uuid4())
uid = str(uuid.uuid4())
# with open(uid+'.mp3','wb') as ff: # with open(uid+'.mp3','wb') as ff:
# ff.write(file_content) # ff.write(file_content)
audio=f'<audio controls id="{uid}" style="display: none"><source src="data:{self.get_mime_type_from_magic(file_content)};base64,{base64_content}"></audio>' audio = f'<audio controls id="{uid}" style="display: none"><source src="data:{self.get_mime_type_from_magic(file_content)};base64,{base64_content}"></audio>'
html_content = audio+html_content.replace(url, f"javascript:document.getElementById('{uid}').play()") html_content = audio + html_content.replace(
file_content=None url,
oked=True f"javascript:document.getElementById('{uid}').play()",
)
file_content = None
oked = True
else: else:
print(url) print(url)
except: except:
file_content=None file_content = None
if file_content: if file_content:
base64_content = base64.b64encode(file_content).decode('utf-8') base64_content = base64.b64encode(file_content).decode("utf-8")
html_content = html_content.replace(url, f'data:application/octet-stream;base64,{base64_content}') html_content = html_content.replace(
url, f"data:application/octet-stream;base64,{base64_content}"
)
elif not oked: elif not oked:
print(url) print(url)
return html_content return html_content
def search(self, word): def search(self, word):
allres = [] allres = []
for index, f in self.builders: for index, f in self.builders:
@ -2555,9 +2566,9 @@ class mdict(cishubase):
print_exc() print_exc()
if len(results) == 0: if len(results) == 0:
continue continue
for i in range(len(results)): for i in range(len(results)):
results[i]=self.repairtarget(index,os.path.dirname(f),results[i]) results[i] = self.repairtarget(index, os.path.dirname(f), results[i])
# <img src="/rjx0849.png" width="1080px"><br><center> <a href="entry://rjx0848"> # <img src="/rjx0849.png" width="1080px"><br><center> <a href="entry://rjx0848">
# /rjx0849.png->mddkey \\rjx0849.png entry://rjx0848->跳转到mdxkey rjx0849 # /rjx0849.png->mddkey \\rjx0849.png entry://rjx0848->跳转到mdxkey rjx0849
# 太麻烦，不搞了。 # 太麻烦，不搞了。

2
LunaTranslator/files/defaultconfig/config.json
View File

@ -979,7 +979,7 @@
"type": "intspin", "type": "intspin",
"name": "ambiguity", "name": "ambiguity",
"min": 0, "min": 0,
"max": 3, "max": 100,
"step": 1 "step": 1
}, },
"priority": { "priority": {