adding fuzzyjoin code to git
diff --git a/asterix-fuzzyjoin/data/pub-small.expected/tokens-000/expected.txt b/asterix-fuzzyjoin/data/pub-small.expected/tokens-000/expected.txt
new file mode 100644
index 0000000..d8e0af0
--- /dev/null
+++ b/asterix-fuzzyjoin/data/pub-small.expected/tokens-000/expected.txt
@@ -0,0 +1,597 @@
+¾_1
+1_1
+2_1
+3_1
+3_2
+4_1
+5_1
+6_1
+80_1
+a_1
+a_2
+abiteboul_1
+abraham_1
+active_1
+adds_1
+ahad_1
+ahmed_1
+aho_1
+albert_1
+alfons_1
+alfred_1
+algorithm_1
+algorithms_1
+alistair_1
+all_1
+allen_1
+amelia_1
+amihai_1
+amit_1
+an_1
+an_2
+analysis_1
+and_1
+and_2
+anders_1
+andrea_1
+andreas_1
+andrew_1
+andrews_1
+angelika_1
+anne_1
+annevelink_1
+application_1
+applications_1
+approach_1
+approaches_1
+architecture_1
+aref_1
+arthur_1
+as_1
+aspnes_1
+authorization_1
+awk_1
+b_1
+bala_1
+ballou_1
+based_1
+beech_1
+benchmark_1
+bernstein_1
+better_1
+beyond_1
+bindings_1
+björnerstedt_1
+blakeley_1
+bloniarz_1
+breitbart_1
+bretl_1
+brian_1
+brom_1
+brozos_1
+bruce_1
+c_1
+c_2
+cad_1
+canonical_1
+capability_1
+carey_1
+carlson_1
+cat_1
+catalyst_1
+chang_1
+changing_1
+chien_1
+choi_1
+chou_1
+chow_1
+chris_1
+christer_1
+christodoulakis_1
+christoph_1
+clarence_1
+classes_1
+claus_1
+clement_1
+commercial_1
+common_1
+comparison_1
+compilers_1
+compressed_1
+computer_1
+concepts_1
+concurrency_1
+concurrent_1
+connors_1
+consensus_1
+contents_1
+control_1
+cooperative_1
+cost_1
+cover_1
+craig_1
+critical_1
+critique_1
+d_1
+dale_1
+dan_1
+dan_2
+daniel_1
+darrell_1
+data_1
+database_1
+databases_1
+david_1
+davis_1
+dayal_1
+dbms_1
+dbmss_1
+declarative_1
+decouchant_1
+dennis_1
+design_1
+deterministic_1
+developing_1
+dewitt_1
+diederich_1
+directions_1
+distributed_1
+dittrich_1
+dittrich_2
+do_1
+dominique_1
+donald_1
+du_1
+e_1
+ealities_1
+early_1
+eda_1
+eduardo_1
+edward_1
+eliot_1
+ellis_1
+engine_1
+engineers_1
+enough_1
+environments_1
+epilogue_1
+eric_1
+eugene_1
+éva_1
+execution_1
+exodus_1
+expected_1
+experiences_1
+extended_1
+extending_1
+f_1
+fast_1
+features_1
+fishman_1
+flow_1
+for_1
+for_2
+form_1
+formal_1
+foundations_1
+frame_1
+frank_1
+fred_1
+frederick_1
+from_1
+future_1
+g_1
+gail_1
+gala_1
+galil_1
+garcia_1
+garcía_1
+garza_1
+gemstone_1
+generation_1
+genome_1
+geometric_1
+geometry_1
+gibbs_1
+gilkey_1
+goodman_1
+graham_1
+graphics_1
+graphs_1
+guide_1
+guido_1
+h_1
+h_2
+hanan_1
+hanson_1
+hardware_1
+harold_1
+hasan_1
+hector_1
+henry_1
+heterogeneity_1
+heterogeneous_1
+heytens_1
+hitting_1
+hoch_1
+hoffmann_1
+hong_1
+hopcroft_1
+hsu_1
+hull_1
+hulten_1
+ibarra_1
+implementation_1
+in_1
+indexing_1
+inegration_1
+inequalities_1
+inference_1
+information_1
+ingram_1
+ingres_1
+injun_1
+integrated_1
+interfaces_1
+interoperability_1
+interoperating_1
+introduction_1
+iris_1
+is_1
+isomorphism_1
+issues_1
+its_1
+j_1
+j_2
+j_3
+jack_1
+jacob_1
+james_1
+jason_1
+java_1
+jeffrey_1
+jennifer_1
+jiang_1
+jik_1
+jim_1
+joel_1
+john_1
+jordan_1
+jorge_1
+josé_1
+jurgen_1
+k_1
+kaiser_1
+kelley_1
+kemper_1
+kent_1
+kernighan_1
+kevin_1
+kifer_1
+kim_1
+kim_2
+king_1
+klaus_1
+knuth_1
+kotz_1
+koveos_1
+kowalski_1
+krieger_1
+kyung_1
+l_1
+lamport_1
+landscape_1
+language_1
+languages_1
+las_1
+latex_1
+laue_1
+lawrence_1
+legacy_1
+leichner_1
+lelescu_1
+leonidas_1
+leslie_1
+lewis_1
+lieberman_1
+lindholm_1
+linear_1
+linear_2
+list_1
+lochovsky_1
+log_1
+log_2
+log²_1
+lorenzo_1
+luks_1
+lunt_1
+lyngbæk_1
+lynn_1
+m_1
+m_2
+machine_1
+mahbod_1
+maier_1
+majorization_1
+making_1
+management_1
+manager_1
+managing_1
+manifolds_1
+manual_1
+mapping_1
+marek_1
+marie_1
+mark_1
+marshall_1
+megiddo_1
+meichun_1
+mellender_1
+meng_1
+message_1
+messages_1
+michael_1
+miguel_1
+milton_1
+min_1
+ming_1
+model_1
+models_1
+modern_1
+moerkotte_1
+moffat_1
+molina_1
+monty_1
+moon_1
+moss_1
+motro_1
+multidatabase_1
+multimedia_1
+multiuser_1
+my_1
+n_1
+n_2
+n²_1
+n_3
+n³_1
+n³log_1
+n_4
+nat_1
+nathan_1
+nc_1
+nc¹_1
+neimat_1
+next_1
+nierstrasz_1
+nikcevic_1
+nimrod_1
+nong_1
+nonmonotonic_1
+o_1
+o_2
+object_1
+object_2
+objects_1
+of_1
+of_2
+office_1
+olkin_1
+omg_1
+omiecinski_1
+on_1
+operations_1
+optimizing_1
+oql_1
+orientation_1
+oriented_1
+orion_1
+orlando_1
+orli_1
+oscar_1
+otis_1
+overview_1
+oz_1
+özsu_1
+p_1
+pairs_1
+parallel_1
+part_1
+path_1
+pegasus_1
+penney_1
+per_1
+performance_1
+peter_1
+philip_1
+physical_1
+pogo_1
+polytopes_1
+posc_1
+possibilities_1
+practice_1
+preface_1
+princiles_1
+probabilistic_1
+problems_1
+processing_1
+processor_1
+program_1
+programming_1
+promises_1
+proposal_1
+proteus_1
+query_1
+r_1
+r³_1
+rafi_1
+rafiul_1
+ralph_1
+rámon_1
+randomized_1
+ravi_1
+ravikumar_1
+reality_1
+reference_1
+references_1
+related_1
+relational_1
+representation_1
+requirements_1
+research_1
+resolving_1
+retrieval_1
+reyes_1
+richard_1
+richardson_1
+riegel_1
+río_1
+risch_1
+robert_1
+roger_1
+rowe_1
+rules_1
+running_1
+rusinkiewicz_1
+russinoff_1
+s_1
+samet_1
+scheevel_1
+schema_1
+schematic_1
+schnorr_1
+schonfeld_1
+schuchardt_1
+search_1
+section_1
+sedgewick_1
+semantics_1
+serge_1
+set_1
+sethi_1
+sets_1
+shan_1
+shared_1
+sharing_1
+shekita_1
+sheth_1
+shortest_1
+should_1
+silberschatz_1
+simon_1
+skarra_1
+smalltalk_1
+snodgrass_1
+software_1
+soley_1
+solution_1
+some_1
+sören_1
+spatial_1
+specification_1
+specifying_1
+sql_1
+stana_1
+standard_1
+standards_1
+stanley_1
+stavros_1
+stein_1
+stephen_1
+steve_1
+steven_1
+stonebraker_1
+storage_1
+story_1
+stout_1
+straw_1
+structures_1
+studies_1
+sunit_1
+support_1
+supporting_1
+survey_1
+system_1
+systems_1
+t_1
+tadao_1
+tai_1
+takaoka_1
+tamer_1
+tao_1
+tardos_1
+tarlton_1
+tarlton_2
+techniques_1
+technology_1
+temporal_1
+teresa_1
+test_1
+tex_1
+the_1
+theory_1
+thompson_1
+tim_1
+time_1
+title_1
+tla_1
+to_1
+tom_1
+tomlinson_1
+tools_1
+tore_1
+tracking_1
+transaction_1
+transactional_1
+transactions_1
+treaty_1
+trivalent_1
+tsichritzis_1
+ullman_1
+umeshwar_1
+uncerainty_1
+ungar_1
+unisql_1
+user_1
+v_1
+vázquez_1
+vázquez_2
+vegs_1
+version_1
+vianu_1
+victor_1
+video_1
+view_1
+vincent_1
+virtual_1
+visual_1
+vortex_1
+w_1
+w_2
+waarts_1
+walid_1
+walker_1
+wand_1
+waqar_1
+war_1
+weber_1
+weimin_1
+weinberger_1
+weintraub_1
+weiser_1
+weiyi_1
+where_1
+widom_1
+wilkinson_1
+william_1
+williams_1
+williams_2
+with_1
+woelk_1
+won_1
+workflows_1
+yair_1
+yellin_1
+yu_1
+yuri_1
+zdonik_1
+zvi_1