Tcl

Regular Expression with Multiple Matches and Capture Groups

See more Regular Expressions Examples

Demonstrates a regular expression with multiple matches and capture groups for each match.

Note: Chilkat uses PCRE2. See PCRE2 Regular Expressions
Also see: PCRE2 Performance

Tcl

load ./chilkat.dll

set success 0

set pattern "Name:\\s+(\\w+)\\s+(\\w+),\\s+Email:\\s+(\\S+)"

set sb [new_CkStringBuilder]

set crlf 1
CkStringBuilder_AppendLine $sb "Name: John Smith, Email: john.smith@example.com" $crlf
CkStringBuilder_AppendLine $sb "Name: Jack Johnson, Email: jack.johnson@example.com" $crlf
CkStringBuilder_AppendLine $sb "Name: Mary Adams, Email: mary.adams@example.com" $crlf

puts [CkStringBuilder_getAsString $sb]

# We have the following string:
# Name: John Smith, Email: john.smith@example.com
# Name: Jack Johnson, Email: jack.johnson@example.com
# Name: Mary Adams, Email: mary.adams@example.com

set json [new_CkJsonObject]

CkJsonObject_put_EmitCompact $json 0

set timeoutMs 2000
set numMatches [CkStringBuilder_RegexMatch $sb $pattern $json $timeoutMs]
if {$numMatches < 0} then {
    # Probably an error in the regular expression.
    # Suggestion: Use AI to help create and/or diagnose regular expressions.
    puts [CkStringBuilder_lastErrorText $sb]
    delete_CkStringBuilder $sb
    delete_CkJsonObject $json
    exit
}

# Examine the matches:
puts [CkJsonObject_emit $json]

# This is the JSON with the match information.
# See the JSON parsing code below to get the matched capture group values.

# {
#   "match": [
#     {
#       "group": [
#         {
#           "cap": "Name: John Smith, Email: john.smith@example.com",
#           "idx": 0,
#           "len": 47
#         },
#         {
#           "cap": "John",
#           "idx": 6,
#           "len": 4
#         },
#         {
#           "cap": "Smith",
#           "idx": 11,
#           "len": 5
#         },
#         {
#           "cap": "john.smith@example.com",
#           "idx": 25,
#           "len": 22
#         }
#       ]
#     },
#     {
#       "group": [
#         {
#           "cap": "Name: Jack Johnson, Email: jack.johnson@example.com",
#           "idx": 49,
#           "len": 51
#         },
#         {
#           "cap": "Jack",
#           "idx": 55,
#           "len": 4
#         },
#         {
#           "cap": "Johnson",
#           "idx": 60,
#           "len": 7
#         },
#         {
#           "cap": "jack.johnson@example.com",
#           "idx": 76,
#           "len": 24
#         }
#       ]
#     },
#     {
#       "group": [
#         {
#           "cap": "Name: Mary Adams, Email: mary.adams@example.com",
#           "idx": 102,
#           "len": 47
#         },
#         {
#           "cap": "Mary",
#           "idx": 108,
#           "len": 4
#         },
#         {
#           "cap": "Adams",
#           "idx": 113,
#           "len": 5
#         },
#         {
#           "cap": "mary.adams@example.com",
#           "idx": 127,
#           "len": 22
#         }
#       ]
#     }
#   ]
# }

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

set i 0
set matchCount [CkJsonObject_SizeOfArray $json "match"]
while {$i < $matchCount} {
    puts "Match [expr $i + 1]:"
    CkJsonObject_put_I $json $i
    set j 0
    set numCaptureGroups [CkJsonObject_SizeOfArray $json "match[i].group"]
    while {$j < $numCaptureGroups} {
        CkJsonObject_put_J $json $j
        set cap [CkJsonObject_stringOf $json "match[i].group[j].cap"]
        puts "$j: $cap"
        set j [expr $j + 1]
    }
    set i [expr $i + 1]
}

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

# Output

# Match 1:
# 0: Name: John Smith, Email: john.smith@example.com
# 1: John
# 2: Smith
# 3: john.smith@example.com
# Match 2:
# 0: Name: Jack Johnson, Email: jack.johnson@example.com
# 1: Jack
# 2: Johnson
# 3: jack.johnson@example.com
# Match 3:
# 0: Name: Mary Adams, Email: mary.adams@example.com
# 1: Mary
# 2: Adams
# 3: mary.adams@example.co

delete_CkStringBuilder $sb
delete_CkJsonObject $json