config.toml

# Configurations

[required]
inputdirectory = "data/in"
outputdirectory = "data/out"
outputmode = "json"          # Options:
# "xml" - Splits zipped bulk XML patents writing each individual XML with all data preserved.
# "json" - Selectively parses patent documents, writing data from each out as a standardized JSON file.
# "parquet" - Selectively parses patent documents, writing all data from a given zip file into a single Parquet file.

[output]
parquetcompression = "snappy" # "snappy" (default), "gzip", "lz4", "zstd", "no-compress"


[logging]
logdirectory = "data/logfiles" # Default is "data/logfiles"
logmode = "prod"               # "prod" (default), "dev"
loglevel = "debug"             # "debug", "info", "warn" (default), "error", "fatal"

[tuning]
# maxconcurrentzips = 0    # Calculated by default and if set to 0
channelbuffersize = 1000 # Default is 100


[dev]
cleanoutput = false      # default false - Deletes output directory at conclusion of runtime,
parserreturnsraw = false # default false - If true, the parser will return the raw split document in addition to parsed data, otherwise it only return the parsed data.