remove trailing comma in mysql2sqlite script using awk gsub - mysql

Question

I found a script to turn a mysql dump into an sqlite insertable code,
and i am trying to get rid of trailing comma's before parentheses. (so the comma after 'DEFAULT NULL'. I use awk and gsub here and there. As you could guess I am not very familiar with regex.
link to script https://gist.github.com/esperlu/943776
CREATE TABLE "table_name" (
"id" INTEGER PRIMARY KEY AUTOINCREMENT,
"name" varchar(100) NOT NULL,
"created_at" datetime NOT NULL,
"deleted_at" datetime DEFAULT NULL,
);
At this point I use the following line in the script:
#Replace trailing commas
/\,\n\)/ { /\,\n\)/, "\, " }
But this gives me the following error in bash
cmd. line:52: /\,\n\)/ { /\,\n\)/, "\, " }
awk: cmd. line:52: ^ syntax error
awk: cmd. line:52: warning: escape sequence `\,' treated as plain `,'
/\,\n\)/ { /\,\n\)/, "\, " }
awk: cmd. line:52: ^ syntax error
awk: cmd. line:52: warning: escape sequence `\,' treated as plain `,'
sql exported to stub-testdb.sqlite
here is my full script into which I added the lines to remove trailing commas
#!/bin/sh
# Converts a mysqldump file into a Sqlite 3 compatible file. It also extracts the MySQL `KEY xxxxx` from the
# CREATE block and create them in separate commands _after_ all the INSERTs.
# Awk is choosen because it's fast and portable. You can use gawk, original awk or even the lightning fast mawk.
# The mysqldump file is traversed only once.
# Usage: $ ./mysql2sqlite mysqldump-opts db-name | sqlite3 database.sqlite
# Example: $ ./mysql2sqlite --no-data -u root -pMySecretPassWord myDbase | sqlite3 database.sqlite
# Thanks to and #artemyk and #gkuenning for their nice tweaks.
mysqldump --compatible=ansi --skip-extended-insert --compact "$#" | \
awk '
# Replace PRIMARY KEY if there is AUTO_INCREMENT
BEGIN { RS="/CREATE TABLE /" }
/NOT NULL AUTO_INCREMENT/ {
gsub( /\n PRIMARY KEY \(\"[a-z_]+\"\)/, "" )
print
next
}
' | \
awk '
BEGIN {
FS=",$"
print "PRAGMA synchronous = OFF;"
print "PRAGMA journal_mode = MEMORY;"
print "BEGIN TRANSACTION;"
}
# CREATE TRIGGER statements have funny commenting. Remember we are in trigger.
/^\/\*.*CREATE.*TRIGGER/ {
gsub( /^.*TRIGGER/, "CREATE TRIGGER" )
print
inTrigger = 1
next
}
# The end of CREATE TRIGGER has a stray comment terminator
/END \*\/;;/ { gsub( /\*\//, "" ); print; inTrigger = 0; next }
# The r est of triggers just get passed through
inTrigger != 0 { print; next }
# Skip other comments
/^\/\*/ { next }
# Print all `INSERT` lines. The single quotes are protected by another single quote.
/INSERT/ {
gsub( /\\\047/, "\047\047" )
gsub(/\\n/, "\n")
gsub(/\\r/, "\r")
gsub(/\\"/, "\"")
gsub(/\\\\/, "\\")
gsub(/\\\032/, "\032")
print
next
}
# Print the `CREATE` line as is and capture the table name.
/^CREATE/ {
print
if ( match( $0, /\"[^\"]+/ ) ) tableName = substr( $0, RSTART+1, RLENGTH-1 )
}
#Replace AUTO_INCREMENT with AUTOINCREMENT
/int\([0-9]+\) NOT NULL AUTO_INCREMENT/ { gsub( /int\([0-9]+\) NOT NULL AUTO_INCREMENT/, "INTEGER PRIMARY KEY AUTOINCREMENT" ) }
#Replace table and column COMMENT
/ COMMENT '.*'/ { gsub( / COMMENT '.*'/, "" ) }
#Replace trailing commas
/\,\n\)/ { /\,\n\)/, "\, " }
# Replace `FULLTEXT KEY` or any other `XXXXX KEY` except PRIMARY by `KEY`
/^ [^"]+KEY/ && !/^ PRIMARY KEY/ { gsub( /.+KEY/, " KEY" ) }
# Get rid of field lengths in KEY lines
/ KEY/ { gsub(/\([0-9]+\)/, "") }
# Print all fields definition lines except the `KEY` lines.
/^ / && !/^( KEY|\);)/ {
gsub( /AUTO_INCREMENT/, "" )
gsub( /(CHARACTER SET|character set) [^ ]+ /, "" )
gsub( /DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP|default current_timestamp on update current_timestamp/, "" )
gsub( /(COLLATE|collate) [^ ]+ /, "" )
gsub(/(ENUM|enum)[^)]+\)/, "text ")
gsub(/(SET|set)\([^)]+\)/, "text ")
gsub(/UNSIGNED|unsigned/, "")
if (prev) print prev ","
prev = $1
}
# `KEY` lines are extracted from the `CREATE` block and stored in array for later print
# in a separate `CREATE KEY` command. The index name is prefixed by the table name to
# avoid a sqlite error for duplicate index name.
/^( KEY|\);)/ {
if (prev) print prev
prev=""
if ($0 == ");"){
print
} else {
if ( match( $0, /\"[^"]+/ ) ) indexName = substr( $0, RSTART+1, RLENGTH-1 )
if ( match( $0, /\([^()]+/ ) ) indexKey = substr( $0, RSTART+1, RLENGTH-1 )
key[tableName]=key[tableName] "CREATE INDEX \"" tableName "_" indexName "\" ON \"" tableName "\" (" indexKey ");\n"
}
}
# Print all `KEY` creation lines.
END {
for (table in key) printf key[table]
print "END TRANSACTION;"
}
'
exit 0

Answer 1

Using GNU awk for multi-char RS and gensub():
$ gawk -v RS='^$' -v ORS= '{$0=gensub(/,(\s*\))/,"\\1","g")}1' file
CREATE TABLE "table_name" (
"id" INTEGER PRIMARY KEY AUTOINCREMENT,
"name" varchar(100) NOT NULL,
"created_at" datetime NOT NULL,
"deleted_at" datetime DEFAULT NULL
);