unzip files with certain extension

[tmcrouse]

I have had some great help on this board and Chris helped me with finding the right path to connect to a shared drive and finding the zipped files. I have 12 folders that have multiple zipped files and I was coding each zipped file as I will show in my code and each .txt file I need from the zipped file. But there are over 200 .txt files in this one zipped folder and I only need the files that have the extension detail.txt. The other files I can disregard. They are flagged.txt. Here is an example of what I have as code now and just want to find an easier way than going back and forth to the shared drive and typing in all these lengthy names:

[code]

filename fromzip zip '\\agpcorp\files\va1\Private\managedcaresvcs\health-qualitymgmt\hedis rates_datasets_benchmarks\hedis 2017\datasets\2016_03_mar hedis 2017_my2016\me1\hedis2017_mar2016_md medicaidchip.zip';

data _null_;

length memname $256;

input memname $;

infile fromzip memvar=memname end=eof;

eof=0;

do while(not eof);

input;

put memname= _infile_;

end;

datalines;

%_rye_mbr_benefit_16_rider16_detail.txt;

adh_med_schizo_16_saa16_detail.txt;

adhere_antipsy_16_am_saa16am_detail.txt;

adol_well_care_16_ch_awc16ch_detail.txt;

adolesc_well_care_16_awc16_detail.txt;

adult_bmi_16_am_aba16am_detail.txt;

adult_bmi_assmt_16_aba16_detail.txt;

adult_access_16_aap16_detail.txt;

ambulatory_care_16_amb16_detail.txt;

ambulatory_care_16_ch_amb16ch_detail.txt;

annual_dental_16_adv16_detail.txt;

annual_mon_rx_16_am_mpm16am_detail.txt;

annual_monitor_rx_16_mpm16_detail.txt;

antemmedmgmntasthma16_mma16wl_detail.txt;

antenatal_stds_16_am_ans16am_detail.txt;

antibiotic_util_16_abx16_detail.txt;

antidepr_meds_16_am_amm16am_detail.txt;

antidepress_meds_16_amm16_detail.txt;

anitpsy_psychosoc_16_app16_detail.txt;

app_test_pharyng_16_cwp16_detail.txt;

app_treatment_uri_16_uri16_detail.txt;

asthma_admit_16_am_aar16am_detail.txt;

asthma_med_ratio_16_amr16_detail.txt;

avoid_abx_bronch_16_aab16_detail.txt;

behavior_risk_16_ch_bra16ch_detail.txt;

breast_cancer_16_am_bcs16am_detail.txt;

cahps_adult_survey_16_cpa16_detail.txt;

cahps_child_16_ch_cpc16ch_detail.txt;

cahps_child_survey_16_cpc16_detail.txt;

breast_cancer_16_bcs16_detail.txt;

cardio_schizo_16_smc_16_detail.txt;

care_trans_16_am_ctr16am_detail.txt;

cervical_c_scr_16_am_ccs16am_detail.txt;

chf_admit_16_am_chf16am_detail.txt;

child_access_16_ch_cap16ch_detail.txt;

child_imm_w_lead_16_cis16q_detail.txt;

childhood_imm_16_ch_cis16ch_detail.txt;

childhood_imm_16_cis16_detail.txt;

childrens_access_16_cap16_detail.txt;

chlamyd_screen_16_ch_chl16ch_detail.txt;

chlamydia_screen_16_chl16_detail.txt;

chlamydia_scrn_16_am_chl16am_detail.txt;

colorectal_cancer_16_col16_detail.txt;

comp_diabetes_16_cdc16_detail.txt;

control_hbp_16_am_cbp16am_detail.txt;

control_high_bp_16_cbp16_detail.txt;

copd_admit_16_am_cpr16am_detail.txt;

csr_for_ntsv_16_ch_csr16ch_detail.txt;

dental_sealant_16_ch_sea16ch_detail.txt;

dev_scrn_1_3_16_ch_dsv16ch_detail.txt;

dev_scrn_age_1_16_ch_dvs16cha_detail.txt;

dev_scrn_age_2_16_ch_dvs16chb_detail.txt;

dev_scrn_age_3_16_ch_dvs16chc_detail.txt;

diab_monit_schizo_16_smd16_detail.txt;

diab_screen_schiz_16_ssd16_detail.txt;

diabetes_a1c_16_am_cdc16am_detail.txt;

diabetes_admit_16_am_dsr16am_detail.txt;

diabetes_poor_16_am_hpc16am_detail.txt;

dmard_rheum_arthr_16_art16_detail.txt;

ed_utilization_16_edu16_detail.txt;

elec_delivery_16_am_edr16am_detail.txt;

fllwup_hosp_mh_16_ch_fuh16ch_detail.txt;

cervical_cancer_16_ccs16_detail.txt;

follow_up_hosp_mh_16_fuh16_detail.txt;

;

[\code]

[ChrisHemedinger]

Hi @tmcrouse, it seems like you might need a two-pass approach for this.  First pass is to assemble the list of TXT files that you need to process, and then for each text file you find, generate a SAS program that does the work of reading in the data from it.  You don't say whether all of the text files have the same format -- it would be good if they do, as that will make things much easier.

Code might look something like this...

filename fromzip zip 'c:\temp\class.zip';
data contents(keep=memname isFolder);
 length memname $200 isFolder 8;
 fid=dopen("fromzip");
 if fid=0 then
  stop;
 memcount=dnum(fid);
 do i=1 to memcount;
  memname=dread(fid,i);
  /* check for trailing / in folder name */
  isFolder = (first(reverse(trim(memname)))='/');
  output;
 end;
 rc=dclose(fid);
run;

options source2;
filename sasprog temp;
data _null_;
 file sasprog;
 length line $ 100;
 set contents(keep=memname);
 lines = 'data in; infile intxt(' || memname || '); input; put _infile_; run;';
 put 'filename intxt ZIP "c:\temp\class.zip";' ;
 put line;
 put 'filename intxt clear;';
run;

%include sasprog;