CQL copy to Cassandra table does not work

Question

I have a tsv file, with records like these:

"county_id" "county_desc"   "voter_reg_num" "status_cd" "voter_status_desc" "reason_cd" "voter_status_reason_desc"  "absent_ind"    "name_prefx_cd" "last_name" "first_name"    "middle_name"   "name_suffix_lbl"   "res_street_address"    "res_city_desc" "state_cd"  "zip_code"  "mail_addr1"    "mail_addr2"    "mail_addr3"    "mail_addr4"    "mail_city" "mail_state"    "mail_zipcode"  "full_phone_number" "race_code" "ethnic_code"   "party_cd"  "gender_code"   "birth_age" "birth_state"   "drivers_lic"   "registr_dt"    "precinct_abbrv"    "precinct_desc" "municipality_abbrv"    "municipality_desc" "ward_abbrv"    "ward_desc" "cong_dist_abbrv"   "super_court_abbrv" "judic_dist_abbrv"  "nc_senate_abbrv"   "nc_house_abbrv"    "county_commiss_abbrv"  "county_commiss_desc"   "township_abbrv"    "township_desc" "school_dist_abbrv" "school_dist_desc"  "fire_dist_abbrv"   "fire_dist_desc"    "water_dist_abbrv"  "water_dist_desc"   "sewer_dist_abbrv"  "sewer_dist_desc"   "sanit_dist_abbrv"  "sanit_dist_desc"   "rescue_dist_abbrv" "rescue_dist_desc"  "munic_dist_abbrv"  "munic_dist_desc"   "dist_1_abbrv"  "dist_1_desc"   "dist_2_abbrv"  "dist_2_desc"   "confidential_ind"  "age"   "ncid"  "vtd_abbrv" "vtd_desc"
"1" "ALAMANCE"  "000009005990"  "A" "ACTIVE"    "AV"    "VERIFIED"  " " " " "AABEL" "EVELYN"    "LARSEN"    ""  "4430 E GREENSBORO-CHAPEL HILL RD   "   "GRAHAM"    "NC"    "27253" "4430 E GREENSBORO-CHAPEL HILL RD"  ""  ""  ""  "GRAHAM"    "NC"    "27253" "0000000"   "W" "NL"    "UNA"   "F" "80"    "NY"    "N" "10/01/1984"    "08N"   "NORTH NEWLIN"  ""  ""  ""  ""  "06"    "15A"   "15A"   "24"    "064"   ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  "15A"   "15A PROSECUTORIAL" " " " " "N" "Age Over 66"   "AA56273"   "08N"   "08N"
"1" "ALAMANCE"  "000009048723"  "A" "ACTIVE"    "AV"    "VERIFIED"  " " " " "AARON" "CHRISTINA" "CASTAGNA"  ""  "421  WHITT AVE   " "BURLINGTON"    "NC"    "27215" "421 WHITT AVE" ""  ""  ""  "BURLINGTON"    "NC"    "27215" "3362291110"    "W" "UN"    "UNA"   "F" "40"    "NC"    "Y" "03/26/1996"    "03S"   "SOUTH BOONE"   "BUR"   "BURLINGTON"    ""  ""  "06"    "15A"   "15A"   "24"    "064"   ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  "BUR"   "BURLINGTON"    "15A"   "15A PROSECUTORIAL" " " " " "N" "Age 26 - 40"   "AA98377"   "03S"   "03S"
"1" "ALAMANCE"  "000009019674"  "A" "ACTIVE"    "AV"    "VERIFIED"  " " " " "AARON" "CLAUDIA"   "HAYDEN"    ""  "1013  EDITH ST   " "BURLINGTON"    "NC"    "27215" "1013 EDITH ST" ""  ""  ""  "BURLINGTON"    "NC"    "27215" "2228834"   "W" "NL"    "UNA"   "F" "71"    "VA"    "Y" "08/15/1989"    "124"   "BURLINGTON 4"  "BUR"   "BURLINGTON"    ""  ""  "06"    "15A"   "15A"   "24"    "063"   ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  "BUR"   "BURLINGTON"    "15A"   "15A PROSECUTORIAL" " " " " "N" "Age Over 66"   "AA69747"   "124"   "124"
"1" "ALAMANCE"  "000009129589"  "A" "ACTIVE"    "AV"    "VERIFIED"  " " " " "AARON" "JAMES" "MICHAEL"   ""  "5608  OLD CHEROKEE LN   "  "GRAHAM"    "NC"    "27253" "PO BOX 98" ""  ""  ""  "SAXAPAHAW" "NC"    "27340" "2027443411"    "W" "UN"    "DEM"   "M" "68"    "MA"    "N" "03/07/2012"    "08N"   "NORTH NEWLIN"  ""  ""  ""  ""  "06"    "15A"   "15A"   "24"    "064"   ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  ""  "15A"   "15A PROSECUTORIAL" " " " " "N" "Age Over 66"   "AA170513"  "08N"   "08N"

And this schema :

create keyspace test with replication  = {'class': 'SimpleStrategy','replication_factor' : 1 };
create table voters(
county_id           varchar,    
county_desc         varchar ,
voter_reg_num       varchar ,
status_cd           varchar ,
voter_status_desc   varchar ,
reason_cd           varchar ,
voter_status_reason_desc    varchar ,
absent_ind          varchar ,
name_prefx_cd       varchar ,
last_name           varchar ,
first_name          varchar ,
midl_name           varchar ,
name_sufx_cd        varchar,
res_street_address  varchar ,
res_city_desc       varchar ,
state_cd            varchar,
zip_code            varchar,
mail_addr1          varchar ,
mail_addr2          varchar ,
mail_addr3          varchar ,
mail_addr4          varchar ,
mail_city           varchar ,
mail_state          varchar,
mail_zipcode        varchar,
full_phone_number   varchar,
race_code           varchar,
ethnic_code         varchar,
party_cd            varchar,
gender_code         varchar,
birth_age           varchar     ,  
birth_place         varchar,
drivers_lic         varchar ,       
registr_dt          varchar,
precinct_abbrv      varchar,
precinct_desc       varchar,
municipality_abbrv  varchar,
municipality_desc   varchar ,
ward_abbrv          varchar,
ward_desc           varchar ,
cong_dist_abbrv     varchar,
super_court_abbrv   varchar,
judic_dist_abbrv    varchar,
nc_senate_abbrv     varchar,
nc_house_abbrv      varchar,
county_commiss_abbrv varchar,
county_commiss_desc     varchar,    
township_abbrv       varchar,
township_desc        varchar,   
school_dist_abbrv    varchar,   
school_dist_desc     varchar,   
fire_dist_abbrv      varchar,   
fire_dist_desc       varchar,   
water_dist_abbrv     varchar,   
water_dist_desc      varchar,   
sewer_dist_abbrv     varchar,   
sewer_dist_desc      varchar,   
sanit_dist_abbrv     varchar,   
sanit_dist_desc      varchar,   
rescue_dist_abbrv    varchar,   
rescue_dist_desc     varchar,   
munic_dist_abbrv     varchar,
munic_dist_desc      varchar,   
dist_1_abbrv         varchar,   
dist_1_desc          varchar,   
dist_2_abbrv         varchar,
dist_2_desc          varchar,   
Confidential_ind     varchar,   
age                 varchar      ,   
ncid                    varchar,     
vtd_abbrv           varchar     ,
vtd_desc            varchar     ,
primary key(voter_reg_num)
);

When I try to copy to a cassandra table, with :

COPY voters FROM 'sample.tsv' WITH DELIMITER='\t';

I get:

Processed: 1000 rows; Rate:    1230 rows/s; Avg. rate:    1945 rows/s
1000 rows imported from 1 files in 0.514 seconds (0 skipped).

However, when I do a count I realize that only one record has been copied to the table.

What am I doing wrong? Thanks in advance.

Answer 1

Add Column name with copy command

COPY voters(county_id,county_desc,voter_reg_num,status_cd,voter_status_desc,reason_cd,voter_status_reason_desc,absent_ind,name_prefx_cd,last_name,first_name,middle_name,name_suffix_lbl,res_street_address,res_city_desc,state_cd,zip_code,mail_addr1,mail_addr2,mail_addr3,mail_addr4,mail_city,mail_state,mail_zipcode,full_phone_number,race_code,ethnic_code,party_cd,gender_code,birth_age,birth_state,drivers_lic,registr_dt,precinct_abbrv,precinct_desc,municipality_abbrv,municipality_desc,ward_abbrv,ward_desc,cong_dist_abbrv,super_court_abbrv,judic_dist_abbrv,nc_senate_abbrv,nc_house_abbrv,county_commiss_abbrv,county_commiss_desc,township_abbrv,township_desc,school_dist_abbrv,school_dist_desc,fire_dist_abbrv,fire_dist_desc,water_dist_abbrv,water_dist_desc,sewer_dist_abbrv,sewer_dist_desc,sanit_dist_abbrv,sanit_dist_desc,rescue_dist_abbrv,rescue_dist_desc,munic_dist_abbrv,munic_dist_desc,dist_1_abbrv,dist_1_desc,dist_2_abbrv,dist_2_desc,confidential_ind,age,ncid,vtd_abbrv,vtd_desc) FROM 'sample.tsv' WITH DELIMITER='\t' AND HEADER = true;

Answer 2

If your tsv file has the columns names at the top, then don't forget to add WITH HEADER = TRUE to your COPY command. I would also remove the double quotes and verify that the fields are separated by tabs and not spaces. To test just create a new tsv file with 50 lines or so from the original and make your changes there. Let me know how it goes.