CkPython

Regular Expression with Multiple Matches and Named Capture Groups

See more Regular Expressions Examples

Demonstrates regular expressions with named capture groups and multiple matches. CkPython

import sys
import chilkat

success = False

sb = chilkat.CkStringBuilder()
crlf = True
sb.AppendLine("Name: John Smith",crlf)
sb.AppendLine("Name: Jack Johnson",crlf)
sb.AppendLine("Name: Mary Adams",crlf)

print(sb.getAsString())

# We have the following string:
# Name: John Smith
# Name: Jack Johnson
# Name: Mary Adams

pattern = "Name:\\s+(?<first>\\w+)\\s+(?<last>\\w+)"
json = chilkat.CkJsonObject()
json.put_EmitCompact(False)

timeoutMs = 2000
numMatches = sb.RegexMatch(pattern,json,timeoutMs)
if (numMatches < 0):
    # Probably an error in the regular expression.
    # Suggestion: Use AI to help create and/or diagnose regular expressions.
    print(sb.lastErrorText())
    sys.exit()

# Examine the matches:
print(json.emit())

# Here is the JSON showing the matches.
# Important:  Capture group 0 always contains the entire match — that is, the portion of the input string that matches the full regular expression.

# {
#   "named": {
#     "first": 1,
#     "last": 2
#   },
#   "match": [
#     {
#       "group": [
#         {
#           "cap": "Name: John Smith",
#           "idx": 0,
#           "len": 16
#         },
#         {
#           "cap": "John",
#           "idx": 6,
#           "len": 4
#         },
#         {
#           "cap": "Smith",
#           "idx": 11,
#           "len": 5
#         }
#       ]
#     },
#     {
#       "group": [
#         {
#           "cap": "Name: Jack Johnson",
#           "idx": 18,
#           "len": 18
#         },
#         {
#           "cap": "Jack",
#           "idx": 24,
#           "len": 4
#         },
#         {
#           "cap": "Johnson",
#           "idx": 29,
#           "len": 7
#         }
#       ]
#     },
#     {
#       "group": [
#         {
#           "cap": "Name: Mary Adams",
#           "idx": 38,
#           "len": 16
#         },
#         {
#           "cap": "Mary",
#           "idx": 44,
#           "len": 4
#         },
#         {
#           "cap": "Adams",
#           "idx": 49,
#           "len": 5
#         }
#       ]
#     }
#   ]
# }

# The capture group index is obtained by looking up the name in the JSON result.
# For example:

idx_first = json.IntOf("named.first")
idx_last = json.IntOf("named.last")

i = 0
matchCount = json.SizeOfArray("match")
while i < matchCount :
    print("Match " + str(i + 1) + ":")
    json.put_I(i)

    json.put_J(idx_first)
    print("first: " + json.stringOf("match[i].group[j].cap"))

    json.put_J(idx_last)
    print("first: " + json.stringOf("match[i].group[j].cap"))

    print("")
    i = i + 1

# Output is: 

# Match 1:
# first: John
# first: Smith
# 
# Match 2:
# first: Jack
# first: Johnson
# 
# Match 3:
# first: Mary
# first: Adams