增加参数R/r的简写，封装匹配方式改变

b4b0b6a7 · 陈森彬 · 80b2746f · b4b0b6a7 · b4b0b6a7 · b4b0b6a7
Commit b4b0b6a7 authored Jan 26, 2021 by 陈森彬
Showing with 59 additions and 10 deletions
config.py
utils/functions.py
valid_server.py
--- a/config.py
+++ b/config.py
@@ -121,13 +121,15 @@ encap_list = ["0030", "008004", "01005", "015008", "0201", "02016", "0202", "020
 temp_map = ["C0G", "NP0", "COG", "NPO", "X7R", "X5R", "Y5V", "X6S", "X7S", "X7T", "SL", "U2J", "UJ", "X7U", "X8R",
            "Z5U", "C0H", "COH", "U2K", "X6T", "X8G", "X8L", "Y5R", "Y5U", "ZLM"]
-unit_regex = "μΩ|uΩ|mΩ|Ω|R|r|kΩ|KΩ|MΩ|GΩ|TΩ|pF|PF|Pf|pf|nF|NF|Nf|nf|µF|μF|uF|UF|Uf|uf|mF|MF|Mf|mf|F|pH|Ph|PH|ph|nH|µH|UH|μh|uh|Uh|uH|mH|Mh|MH|mh|H|mA|A|a|V|v|kV|Kv|kv|KV|W|w|kW|kw|KW|Kw|%|毫欧|欧姆|欧|千欧|兆欧|伏特|伏|千伏|瓦特|瓦"
+unit_regex = "μΩ|uΩ|mΩ|Ω|kΩ|KΩ|MΩ|GΩ|TΩ|pF|PF|Pf|pf|nF|NF|Nf|nf|µF|μF|uF|UF|Uf|uf|mF|MF|Mf|mf|F|pH|Ph|PH|ph|nH|µH|UH|μh|uh|Uh|uH|mH|Mh|MH|mh|H|mA|A|a|V|v|kV|Kv|kv|KV|W|w|kW|kw|KW|Kw|%|毫欧|欧姆|欧|千欧|兆欧|伏特|伏|千伏|瓦特|瓦"
+r_regex = "Rr"
 encap_regex = "0030|008004|01005|015008|0201|02016|0202|0204|03015|03019|0302|0303|0306|0402|0404|0405|0406|0502|0503|0504|0505|0508|0602|0603|0604|0605|0606|0612|0704|0707|0709|0803|0804|0805|0806|0815|0830|0905|0909|1003|1005|1006|1007|1008|1010|1012|1020|1106|1111|1113|1204|1205|1206|1207|1208|1209|1210|1211|1212|1213|1218|1225|1230|1246|1305|1410|1411|1412|1414|1505|1507|1510|1512|1515|1530|1606|1608|1611|1612|1616|1625|1708|1715|1805|1806|1807|1808|1810|1812|1816|1825|1835|1913|1916|1919|2005|2008|2010|2015|2016|2018|2020|2023|2043|2211|2214|2215|2218|2220|2225|2304|2312|2323|2325|2410|2414|2416|2420|2423|2424|2512|2520|2525|2615|2616|2706|2709|2711|2721|2727|2728|2812|2820|2824|2825|2828|2830|2910|2913|2915|2917|2920|2924|3010|3015|3017|3022|3024|3025|3040|3131|3225|3226|3312|3318|3333|3640|3838|3920|3925|3931|4030|4032|4122|4520|4823|4850|5040|5329|5829|5929|6028|6030|6031|6039|6054|6560"
-encap_par_start = ",| /，-"
+legal_char = 'CRL'
-encap_par_str = ",| /，-CRL"
+split_char = '|,，/ '
 special_tuple = ("-",)

--- a/utils/functions.py
+++ b/utils/functions.py
 #!/usr/bin/env python
 # -*- coding:utf-8 -*-
 import re
-from config import unit_map, cast_map, unit_regex, special_tuple, encap_list, temp_map, special_str, encap_regex
+from config import unit_map, cast_map, unit_regex, special_tuple, encap_list, temp_map, special_str, encap_regex, \
+    r_regex, legal_char, split_char
 unit_pattern = re.compile('([.a-zA-Z\\-]?)(\d+|\d+[\\\./?]\d+)(' + unit_regex + ')([.a-zA-Z\\-]?)')
-encap_pattern = re.compile('.*(' + encap_regex + ').*')
+r_pattern = re.compile(
+    '([.a-zA-Z\\-]?)(\d+[' + r_regex + ']\d+|[' + r_regex + ']\d+|\d+[' + r_regex + '])([.a-zA-Z\\-]?)')
+encap_pattern = re.compile('(.{0,2})(' + encap_regex + ')(.{0,2})', re.I)
+prefixchar = [i + j for i in split_char for j in legal_char]
+tailchar = [i + j for i in legal_char for j in split_char]
+prefixchar.extend(list(legal_char))
+tailchar.extend(list(split_char))
+prefixchar.append('')
+tailchar.append('')
 def is_float(s):
@@ -179,6 +188,21 @@ def get_not_exist_list(attrs_list, cut_list):
    return not_exist_list
+def valid_encap(prefix, tail):
+    prefix_flag = False
+    tail_flag = False
+    if prefix in prefixchar or prefix[-1] in split_char:
+        prefix_flag = True
+    if tail in tailchar or tail[0] in split_char:
+        tail_flag = True
+    if prefix_flag and tail_flag:
+        return True
+    return False
 def check_encap(kw):
    """
    确认是不是封装
@@ -187,7 +211,9 @@ def check_encap(kw):
    """
    encap_res = encap_pattern.findall(kw)
    if encap_res:
-        return encap_res
+        encap_res = encap_res[0]
+        if valid_encap(encap_res[0], encap_res[2]):
+            return encap_res[1]
    return False
@@ -213,6 +239,25 @@ def check_symbol(kw):
    return False
+def check_param_r(kw):
+    check_res = r_pattern.findall(kw)
+    if not check_res:
+        check_res = False
+    else:
+        check_res = check_res[0]
+        new_list = []
+        if not check_res[0].isalpha() and not check_res[2].isalpha():
+            cut_list = re.split('[Rr]', check_res[1])
+            if not cut_list[0] and cut_list[1]:
+                new_list.append("0." + str(cut_list[1]) + "Ω")
+            elif cut_list[0] and not cut_list[1]:
+                new_list.append(str(cut_list[0]) + "Ω")
+            else:
+                new_list.append(check_res[1].replace("R", ".").replace("r", ".") + "Ω")
+        check_res = new_list
+    return check_res
 def get_unit(unit_list):
    unit_str = ""
    for u_str in unit_list:

--- a/valid_server.py
+++ b/valid_server.py
@@ -7,7 +7,7 @@ import tornado.web
 import tornado.ioloop
 from utils.functions import pre_judge, word_conversion, cut_params, check_param, unit_conversion, get_not_exist_list, \
-    check_encap, check_temp, check_symbol
+    check_encap, check_temp, check_symbol, check_param_r
 from utils.redis_cli import redis_cli
 from predict.kw_predict import KwPredict
@@ -131,12 +131,14 @@ class UCHandler(tornado.web.RequestHandler):
                for kw_info in unknown_list:
                    if check_temp(kw_info):
                        attrs_list.append(kw_info)
+                    elif check_param_r(kw_info):
+                        attrs_list.append(check_param_r(kw_info)[0])
                    else:
                        encap_res = check_encap(kw_info)
                        if encap_res:
-                            encap_list.append(encap_res[0])
+                            encap_list.append(encap_res)
-                            continue
-                        if kw_info and check_symbol(kw_info):
+                        if kw_info and check_symbol(kw_info) and not encap_res:
                            words_list.append(kw_info)
            res['status'] = 1