comparison lxmldump.py @ 19:7c6eb57798bd

Ja niin.
author Matti Hamalainen <ccr@tnsp.org>
date Tue, 11 May 2021 16:15:16 +0300
parents ff959de0f6c8
children f274504eafd0
comparison
equal deleted inserted replaced
18:ff959de0f6c8 19:7c6eb57798bd
40 "ahavakala", 40 "ahavakala",
41 "ahavakoittuo", 41 "ahavakoittuo",
42 "ahvaliha", 42 "ahvaliha",
43 "aloilleh", 43 "aloilleh",
44 "hanjahtoakseh", 44 "hanjahtoakseh",
45 "akkalisto",
45 ] 46 ]
46 47
47 48
48 ### 49 ###
49 ### Misc. helper functions, etc 50 ### Misc. helper functions, etc
182 tmpl = [] 183 tmpl = []
183 for pnode in wnode.findall("./PartOfSpeechCtn/PartOfSpeech"): 184 for pnode in wnode.findall("./PartOfSpeechCtn/PartOfSpeech"):
184 tmpl.append(pnode.attrib["freeValue"]) 185 tmpl.append(pnode.attrib["freeValue"])
185 186
186 for pnode in wnode.findall("./GrammaticalNote"): 187 for pnode in wnode.findall("./GrammaticalNote"):
187 tmpl.append(pnode.text.strip()) 188 tmpl.append(pkk_node_to_text(pnode))
188 189
189 # Remove duplicates and sort the list 190 # Remove duplicates and sort the list
190 tmpl = list(set(tmpl)) 191 tmpl = list(set(tmpl))
191 tmpl.sort(reverse=False, key=lambda attr: (attr, len(attr))) 192 tmpl.sort(reverse=False, key=lambda attr: (attr, len(attr)))
192 193
302 303
303 if pkk_cfg["debug"] and dnode.attrib["identifier"] not in pkk_debug_list: 304 if pkk_cfg["debug"] and dnode.attrib["identifier"] not in pkk_debug_list:
304 continue 305 continue
305 306
306 if pkk_cfg["mode"] == 0: 307 if pkk_cfg["mode"] == 0:
307 pkk_output_node(0, dnode) 308 try:
309 pkk_output_node(0, dnode)
310 except Exception as e:
311 pkk_dump_recursive(0, dnode)
312 print(str(e))
313 sys.exit(0)
308 elif pkk_cfg["mode"] == 1: 314 elif pkk_cfg["mode"] == 1:
309 pkk_dump_recursive(0, dnode) 315 pkk_dump_recursive(0, dnode)
310 elif pkk_cfg["mode"] == 2: 316 elif pkk_cfg["mode"] == 2:
311 pkk_print(str(xmlET.tostring(dnode, encoding="utf8")) + "\n") 317 pkk_print(str(xmlET.tostring(dnode, encoding="utf8")) + "\n")
312 else: 318 else: