Fixes Cheat Sheet
This cheat sheet summarizes the fix language.
# Fixes clean your data. As input you get a Perl HASH. Each fix function is a command
# to transform the Perl HASH. Some fixes such as marc_map contain logic to transform
# complex data structures such as MARC.
set_field("my.name","patrick") # { my => { name => 'Patrick'} }
add_field("my.name2","nicolas")
move_field("my.name","your.name")
copy_field("your.name","your.name2")
remove_field("your.name")
set_array("foo") # Create an empty array foo => []
set_array("foo","a","b","c") # Create an array with three values foo => ['a','b','c']
set_hash("foo") # Create an empty hash foo => {}
set_hash("foo",a: b,c: d) # Create an hash with two values foo => { a => 'b' , c => 'd' }
array("foo") # Create an array from a hash :
# foo => {"name":"value"} => [ "name" , "value" ]
hash("foo") # Create a hash from an array
# foo => [ "name" , "value" ] => {"name":"value"}
assoc(fields, pairs.*.key, pairs.*.val) # Associate two values as a hash key and value
# {pairs => [{key => 'year', val => 2009}, {key => 'subject', val => 'Perl'}]}
# {fields => {subject => 'Perl', year => 2009}, pairs => [...]}
upcase("title") # marc -> MARC
downcase("title") # MARC -> marc
capitalize("my.deeply.nested.field.0") # marc -> Marc
trim("field_with_spaces") # " marc " -> marc
substring("title",0,1) # marc -> m
prepend("title","die ") # marc -> die marc
append("title"," must die") # marc -> marc must die
# replace the value with a formatted (sprintf-like) version
# e.g. numbers:
# - 41
# - 15
format(number,"%-10.10d %-5.5d") # numbers => "0000000041 00015"
# e.g. hash:
# name: Albert
format(name,"%-10s: %s") # hash: "name : Albert"
# date: "2015-03-07"
parse_text(date, '(\d\d\d\d)-(\d\d)-(\d\d)')
# date:
# - 2015
# - 03
# - 07
# parses a text into an array or hash of values
# date: "2015-03-07"
parse_text(date, '(\d\d\d\d)-(\d\d)-(\d\d)')
# date:
# - 2015
# - 03
# - 07
# date: "2015-03-07"
parse_text(date, '(?<year>\d\d\d\d)-(?<month>\d\d)-(?<day>\d\d)')
# date:
# year: "2015"
# month: "03"
# day: "07"
# date: "abcd"
parse_text(date, '(\d\d\d\d)-(\d\d)-(\d\d)')
# date: "abcd"
lookup("title","dict.csv", sep_char:'|') # lookup 'marc' in dict.csv and replace the value
lookup("title","dict.csv", default:test) # lookup 'marc' in dict.csv and replace the value or set it to 'test'
lookup("title","dict.csv", delete:1) # lookup 'marc' in dict.csv and replace the value or delete nothing found
lookup_in_store('title', 'MongoDB', database_name:lookups) # lookup the (id)-value of title in 'lookups' and
# replace it with the data found
lookup_in_store('title', 'MongoDB', default:'default value' , delete:1)
# Replace the data in foo.bar with an external file or url
import(foo.bar, JSON, file: "http://foo.com/bar.json", data_path: data.*)
add_to_store('authors.*', 'MongoDB', bag:authors, database_name:catalog) # add matching values to a store as a side effect
add_to_exporter(data,CSV,header:1,file:/tmp/data.csv) # send the 'data' path to an alternative exporter
add_to_exporter(.,CSV,header:1,file:/tmp/data.csv) # send the complete record to an alternative exporter
count("myarray") # count number of elements in an array or hash
sum("numbers") # replace an array element with the sum of its values
sort_field("tags") # sort the values of an array
sort_field("tags", uniq:1) # sort the values plus keep unique values
sort_field("tags", reverse:1) # revese sort
sort_field("tags", numeric:1) # sort numerical values
filter("tags","[Cc]at") # filter array values tags = ["Cats","Dogs"] => ["Cats"]
flatten(deep) # {deep => [1, [2, 3], 4, [5, [6, 7]]]} => {deep => [1, 2, 3, 4, 5, 6, 7]}
cmd("java MyClass") # Use an external program that can read JSON
# from stdin and write JSON to stdout
perlcode("myscript.pl") # Execute Perl code as fix function
split_field("foo",":") # marc:must:die -> ['marc','must','die']
join_field("foo",":") # ['marc','must','die'] -> marc:must:die
retain_field("id") # delete any field except 'id'
replace_all("title","a","x") # marc -> mxrc
# Most functions can work also work on arrays. E.g.
replace_all("author.*","a","x") # [ 'marc','jan'] => ['mxrc','jxn']
# Use:
# authors.$end (last entry)
# authors.$start (first entry)
# authors.$append (last + 1)
# authors.$prepend (first - 1)
# authors.* (all authors)
# authors.2 (3rd author)
collapse() # collapse deep nested hash to a flat hash
expand() # expand flat hash to deep nested hash
clone() # clone the perl hash and work on the clone
reject() # Reject (skip) a record
reject [condition] # Reject a record on some condition:
# reject all_match(...)
# reject any_match(...)
# reject exists(...)
select() # Select a record
select [condition] # Select only those records that match a condition (see reject)
to_json('my.field') # convert a value of a field to json
from_json('my.field') # replace the json field with the parsed value
nothing() # do nothing (used in benchmarking)
# Copy all 245 subfields into the my.title hash
marc_map('245','my.title')
# Copy the 245-$a$b$c subfields into the my.title hash in the order of the record
marc_map('245abc','my.title')
# Copy the 245-$c$b$a subfields into the my.title hash in the order of the mapping
marc_map('245cba','my.title' , pluck:1)
# Copy the 100 subfields into the my.authors array
marc_map('100','my.authors.$append')
# Add the 710 subfields into the my.authors array
marc_map('710','my.authors.$append')
# Copy the 600-$x subfields into the my.subjects array while packing each into a genre.text hash
marc_map('600x','my.subjects.$append.genre.text')
# Copy the 008 characters 35-35 into the my.language hash
marc_map('008_/35-35','my.language')
# Copy all the 600 fields into a my.stringy hash joining them by '; '
marc_map('600','my.stringy', join:'; ')
# When 024 field exists create the my.has024 hash with value 'found'
marc_map('024','my.has024', value:found)
# Do the same examples now with the marc fields in 'record2'
marc_map('245','my.title', record:record2)
# Remove the 900 fields
marc_remove('900')
# Add a marc field (in Catmandu::MARC 0.110)
marc_add('999', ind1:' ' , ind2:'1' , a:'test123')
# Set a marc value of one (sub)field to a new value
marc_set('LDR/6','p')
marc_set('650p','test')
marc_set('100[3]a','Farquhar family.')
# Map all 650 subjects into an array
marc_map('650','subject', join:'###')
split_field('subject','###')
# Include fixes from another file
include('/path/to/myfixes.txt')
# Send debug messages to a logger
log('test123')
log('hello world' , level => 'DEBUG')
# uppercase the value of field 'foo' if all members of 'oogly' have the value 'doogly'
if all_match('oogly.*', 'doogly')
upcase('foo') # foo => 'BAR'
else
downcase('foo') # foo => 'bar'
end
# inverted
unless all_match('oogly.*', 'doogly')
upcase('foo') # foo => 'BAR'
end;
# uppercase the value of field 'foo' if field 'oogly' has the value 'doogly'
if any_match('oogly', 'doogly')
upcase('foo') # foo => 'BAR'
end
# inverted
unless any_match('oogly', 'doogly')
upcase('foo') # foo => 'BAR'
end
# uppercase the value of field 'foo' if the field 'oogly' exists
if exists('oogly')
upcase('foo') # foo => 'BAR'
end
# inverted
unless exists('oogly')
upcase('foo') # foo => 'bar'
end
# add a new field when the 'year' field is equal to 2018
if all_equal('year','2018')
add_field('my.funny.title','true')
end
# add a new field when at least one of the 'year'-s is equal to 2018
if any_equal('years.*','2018')
add_field('my.funny.title','true')
end
# compare things (needs Catmandu 0.92 or better)
if greater_than('year',2000)
add_field('recent','yes')
end
if less_than('year',1970)
add_field('ancient','yes')
end
# execute fixes if one path is contained in another
# foo => 1 , bar => [3,2,1] => in(foo,bar) -> true
if in(foo,bar)
add_field(test,ok)
end
# only execute fixes if all path values are the boolean true, 1 or "true"
if is_true(data.*.has_error)
add_field(error,yes)
end
# only execute fixes if all path values are the boolean true, 0 or "false"
if is_false(data.*.has_error)
add_field(error,no)
end
# Evaludates true when a marc (sub)field matches a regular expression
if marc_match('245','My funny title')
add_field('funny.title','yes')
end
if marc_match('LDR/6','c')
marc_set('LDR/6','p')
end
## Binds (needs Catmandu 0.92 or better)
# The identity binder doesn't embody any computational strategy. It simply
# applies the bound fix functions sequentially to its input without any
# modification.
do identity()
add_field(foo,bar)
add_field(foo2,bar2)
end
# Maybe, computes all the fix functions and ignores fixes once they throw errors
# or return undef.
do maybe()
foo()
return_undef() # rest will be ignored
bar()
end
# List over all items in demo and add a foo => bar field
# { demo => [{},{},{}] } => { demo => [{foo=>bar},{foo=>bar},{foo=>bar}]}
do list(path: demo)
add_field(foo,bar)
end
# Print statistical information on the processing speed of fixes to the standaard error.
do benchmark(output:/dev/stderr)
foo()
end
# Find all ISBN in a stream
do hashmap(exporter: JSON, join:',')
# Need an identity binder to group all operations that calculate key_value pairs
do identity()
copy_field(isbn,key)
copy_field(_id,value)
end
end
# Count the number of ISBN occurrences in a stream
do hashmap(count: 1)
copy_field(isbn,key)
end
# Filter out an array (needs Catmandu 0.9302 or better)
# data:
# - name: patrick
# - name: nicolas
# to:
# data:
# - name: patrick
do with(path:data)
reject all_match(name,nicolas)
# Or:
# if all_match(name,nicolas)
# reject()
# end
end