Stata lexer and styles improvements and bug fixes

- Nested comments correctly highlighted.
- Globals and locals correctly nested inside each other and strings.
- Extended locals and stored results correctly highlighted.
- Keywords and operators correctly highlighted.
- Parentheses and functions correctly highlighted.

6 files changed, 622 insertions, 489 deletions

diff --git a/pygments/lexers/_stata_builtins.py b/pygments/lexers/_stata_builtins.py
new file mode 100644
index 00000000..13a3dacf
--- /dev/null
+++ b/pygments/lexers/_stata_builtins.py
@@ -0,0 +1,421 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.lexers._stata_builtins
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Builtins for Stata
+
+    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+
+builtins_special = (
+    "if", "in", "using", "replace", "by", "gen", "generate"
+)
+
+builtins_base = (
+    "if", "else", "else\s+if", "in", "foreach", "for", "forv", "forva",
+    "forval", "forvalu", "forvalue", "forvalues", "by", "bys",
+    "bysort", "quietly", "qui", "about", "ac",
+    "ac_7", "acprplot", "acprplot_7", "adjust", "ado", "adopath",
+    "adoupdate", "alpha", "ameans", "an", "ano", "anov", "anova",
+    "anova_estat", "anova_terms", "anovadef", "aorder", "ap", "app",
+    "appe", "appen", "append", "arch", "arch_dr", "arch_estat",
+    "arch_p", "archlm", "areg", "areg_p", "args", "arima",
+    "arima_dr", "arima_estat", "arima_p", "as", "asmprobit",
+    "asmprobit_estat", "asmprobit_lf", "asmprobit_mfx__dlg",
+    "asmprobit_p", "ass", "asse", "asser", "assert", "avplot",
+    "avplot_7", "avplots", "avplots_7", "bcskew0", "bgodfrey",
+    "binreg", "bip0_lf", "biplot", "bipp_lf", "bipr_lf",
+    "bipr_p", "biprobit", "bitest", "bitesti", "bitowt", "blogit",
+    "bmemsize", "boot", "bootsamp", "bootstrap", "bootstrap_8",
+    "boxco_l", "boxco_p", "boxcox", "boxcox_6", "boxcox_p",
+    "bprobit", "br", "break", "brier", "bro", "brow", "brows",
+    "browse", "brr", "brrstat", "bs", "bs_7", "bsampl_w",
+    "bsample", "bsample_7", "bsqreg", "bstat", "bstat_7", "bstat_8",
+    "bstrap", "bstrap_7", "ca", "ca_estat", "ca_p", "cabiplot",
+    "camat", "canon", "canon_8", "canon_8_p", "canon_estat",
+    "canon_p", "cap", "caprojection", "capt", "captu", "captur",
+    "capture", "cat", "cc", "cchart", "cchart_7", "cci",
+    "cd", "censobs_table", "centile", "cf", "char", "chdir",
+    "checkdlgfiles", "checkestimationsample", "checkhlpfiles",
+    "checksum", "chelp", "ci", "cii", "cl", "class", "classutil",
+    "clear", "cli", "clis", "clist", "clo", "clog", "clog_lf",
+    "clog_p", "clogi", "clogi_sw", "clogit", "clogit_lf",
+    "clogit_p", "clogitp", "clogl_sw", "cloglog", "clonevar",
+    "clslistarray", "cluster", "cluster_measures", "cluster_stop",
+    "cluster_tree", "cluster_tree_8", "clustermat", "cmdlog",
+    "cnr", "cnre", "cnreg", "cnreg_p", "cnreg_sw", "cnsreg",
+    "codebook", "collaps4", "collapse", "colormult_nb",
+    "colormult_nw", "compare", "compress", "conf", "confi",
+    "confir", "confirm", "conren", "cons", "const", "constr",
+    "constra", "constrai", "constrain", "constraint", "continue",
+    "contract", "copy", "copyright", "copysource", "cor", "corc",
+    "corr", "corr2data", "corr_anti", "corr_kmo", "corr_smc",
+    "corre", "correl", "correla", "correlat", "correlate",
+    "corrgram", "cou", "coun", "count", "cox", "cox_p", "cox_sw",
+    "coxbase", "coxhaz", "coxvar", "cprplot", "cprplot_7",
+    "crc", "cret", "cretu", "cretur", "creturn", "cross", "cs",
+    "cscript", "cscript_log", "csi", "ct", "ct_is", "ctset",
+    "ctst_5", "ctst_st", "cttost", "cumsp", "cumsp_7", "cumul",
+    "cusum", "cusum_7", "cutil", "d", "datasig", "datasign",
+    "datasigna", "datasignat", "datasignatu", "datasignatur",
+    "datasignature", "datetof", "db", "dbeta", "de", "dec",
+    "deco", "decod", "decode", "deff", "des", "desc", "descr",
+    "descri", "describ", "describe", "destring", "dfbeta",
+    "dfgls", "dfuller", "di", "di_g", "dir", "dirstats", "dis",
+    "discard", "disp", "disp_res", "disp_s", "displ", "displa",
+    "display", "distinct", "do", "doe", "doed", "doedi",
+    "doedit", "dotplot", "dotplot_7", "dprobit", "drawnorm",
+    "drop", "ds", "ds_util", "dstdize", "duplicates", "durbina",
+    "dwstat", "dydx", "e", "ed", "edi", "edit", "egen",
+    "eivreg", "emdef", "end", "en", "enc", "enco", "encod", "encode",
+    "eq", "erase", "ereg", "ereg_lf", "ereg_p", "ereg_sw",
+    "ereghet", "ereghet_glf", "ereghet_glf_sh", "ereghet_gp",
+    "ereghet_ilf", "ereghet_ilf_sh", "ereghet_ip", "eret",
+    "eretu", "eretur", "ereturn", "err", "erro", "error", "est",
+    "est_cfexist", "est_cfname", "est_clickable", "est_expand",
+    "est_hold", "est_table", "est_unhold", "est_unholdok",
+    "estat", "estat_default", "estat_summ", "estat_vce_only",
+    "esti", "estimates", "etodow", "etof", "etomdy", "ex",
+    "exi", "exit", "expand", "expandcl", "fac", "fact", "facto",
+    "factor", "factor_estat", "factor_p", "factor_pca_rotated",
+    "factor_rotate", "factormat", "fcast", "fcast_compute",
+    "fcast_graph", "fdades", "fdadesc", "fdadescr", "fdadescri",
+    "fdadescrib", "fdadescribe", "fdasav", "fdasave", "fdause",
+    "fh_st", "open", "read", "close",
+    "file", "filefilter", "fillin", "find_hlp_file", "findfile",
+    "findit", "findit_7", "fit", "fl", "fli", "flis", "flist",
+    "for5_0", "form", "forma", "format", "fpredict", "frac_154",
+    "frac_adj", "frac_chk", "frac_cox", "frac_ddp", "frac_dis",
+    "frac_dv", "frac_in", "frac_mun", "frac_pp", "frac_pq",
+    "frac_pv", "frac_wgt", "frac_xo", "fracgen", "fracplot",
+    "fracplot_7", "fracpoly", "fracpred", "fron_ex", "fron_hn",
+    "fron_p", "fron_tn", "fron_tn2", "frontier", "ftodate", "ftoe",
+    "ftomdy", "ftowdate", "g", "gamhet_glf", "gamhet_gp",
+    "gamhet_ilf", "gamhet_ip", "gamma", "gamma_d2", "gamma_p",
+    "gamma_sw", "gammahet", "gdi_hexagon", "gdi_spokes", "ge",
+    "gen", "gene", "gener", "genera", "generat", "generate",
+    "genrank", "genstd", "genvmean", "gettoken", "gl", "gladder",
+    "gladder_7", "glim_l01", "glim_l02", "glim_l03", "glim_l04",
+    "glim_l05", "glim_l06", "glim_l07", "glim_l08", "glim_l09",
+    "glim_l10", "glim_l11", "glim_l12", "glim_lf", "glim_mu",
+    "glim_nw1", "glim_nw2", "glim_nw3", "glim_p", "glim_v1",
+    "glim_v2", "glim_v3", "glim_v4", "glim_v5", "glim_v6",
+    "glim_v7", "glm", "glm_6", "glm_p", "glm_sw", "glmpred", "glo",
+    "glob", "globa", "global", "glogit", "glogit_8", "glogit_p",
+    "gmeans", "gnbre_lf", "gnbreg", "gnbreg_5", "gnbreg_p",
+    "gomp_lf", "gompe_sw", "gomper_p", "gompertz", "gompertzhet",
+    "gomphet_glf", "gomphet_glf_sh", "gomphet_gp", "gomphet_ilf",
+    "gomphet_ilf_sh", "gomphet_ip", "gphdot", "gphpen",
+    "gphprint", "gprefs", "gprobi_p", "gprobit", "gprobit_8", "gr",
+    "gr7", "gr_copy", "gr_current", "gr_db", "gr_describe",
+    "gr_dir", "gr_draw", "gr_draw_replay", "gr_drop", "gr_edit",
+    "gr_editviewopts", "gr_example", "gr_example2", "gr_export",
+    "gr_print", "gr_qscheme", "gr_query", "gr_read", "gr_rename",
+    "gr_replay", "gr_save", "gr_set", "gr_setscheme", "gr_table",
+    "gr_undo", "gr_use", "graph", "graph7", "grebar", "greigen",
+    "greigen_7", "greigen_8", "grmeanby", "grmeanby_7",
+    "gs_fileinfo", "gs_filetype", "gs_graphinfo", "gs_stat",
+    "gsort", "gwood", "h", "hadimvo", "hareg", "hausman",
+    "haver", "he", "heck_d2", "heckma_p", "heckman", "heckp_lf",
+    "heckpr_p", "heckprob", "hel", "help", "hereg", "hetpr_lf",
+    "hetpr_p", "hetprob", "hettest", "hexdump", "hilite",
+    "hist", "hist_7", "histogram", "hlogit", "hlu", "hmeans",
+    "hotel", "hotelling", "hprobit", "hreg", "hsearch", "icd9",
+    "icd9_ff", "icd9p", "iis", "impute", "imtest", "inbase",
+    "include", "inf", "infi", "infil", "infile", "infix", "inp",
+    "inpu", "input", "ins", "insheet", "insp", "inspe",
+    "inspec", "inspect", "integ", "inten", "intreg", "intreg_7",
+    "intreg_p", "intrg2_ll", "intrg_ll", "intrg_ll2", "ipolate",
+    "iqreg", "ir", "irf", "irf_create", "irfm", "iri", "is_svy",
+    "is_svysum", "isid", "istdize", "ivprob_1_lf", "ivprob_lf",
+    "ivprobit", "ivprobit_p", "ivreg", "ivreg_footnote",
+    "ivtob_1_lf", "ivtob_lf", "ivtobit", "ivtobit_p", "jackknife",
+    "jacknife", "jknife", "jknife_6", "jknife_8", "jkstat",
+    "joinby", "kalarma1", "kap", "kap_3", "kapmeier", "kappa",
+    "kapwgt", "kdensity", "kdensity_7", "keep", "ksm", "ksmirnov",
+    "ktau", "kwallis", "l", "la", "lab", "labe", "label",
+    "labelbook", "ladder", "levels", "levelsof", "leverage",
+    "lfit", "lfit_p", "li", "lincom", "line", "linktest",
+    "lis", "list", "lloghet_glf", "lloghet_glf_sh", "lloghet_gp",
+    "lloghet_ilf", "lloghet_ilf_sh", "lloghet_ip", "llogi_sw",
+    "llogis_p", "llogist", "llogistic", "llogistichet",
+    "lnorm_lf", "lnorm_sw", "lnorma_p", "lnormal", "lnormalhet",
+    "lnormhet_glf", "lnormhet_glf_sh", "lnormhet_gp",
+    "lnormhet_ilf", "lnormhet_ilf_sh", "lnormhet_ip", "lnskew0",
+    "loadingplot", "loc", "loca", "local", "log", "logi",
+    "logis_lf", "logistic", "logistic_p", "logit", "logit_estat",
+    "logit_p", "loglogs", "logrank", "loneway", "lookfor",
+    "lookup", "lowess", "lowess_7", "lpredict", "lrecomp", "lroc",
+    "lroc_7", "lrtest", "ls", "lsens", "lsens_7", "lsens_x",
+    "lstat", "ltable", "ltable_7", "ltriang", "lv", "lvr2plot",
+    "lvr2plot_7", "m", "ma", "mac", "macr", "macro", "makecns",
+    "man", "manova", "manova_estat", "manova_p", "manovatest",
+    "mantel", "mark", "markin", "markout", "marksample", "mat",
+    "mat_capp", "mat_order", "mat_put_rr", "mat_rapp", "mata",
+    "mata_clear", "mata_describe", "mata_drop", "mata_matdescribe",
+    "mata_matsave", "mata_matuse", "mata_memory", "mata_mlib",
+    "mata_mosave", "mata_rename", "mata_which", "matalabel",
+    "matcproc", "matlist", "matname", "matr", "matri",
+    "matrix", "matrix_input__dlg", "matstrik", "mcc", "mcci",
+    "md0_", "md1_", "md1debug_", "md2_", "md2debug_", "mds",
+    "mds_estat", "mds_p", "mdsconfig", "mdslong", "mdsmat",
+    "mdsshepard", "mdytoe", "mdytof", "me_derd", "mean",
+    "means", "median", "memory", "memsize", "meqparse", "mer",
+    "merg", "merge", "mfp", "mfx", "mhelp", "mhodds", "minbound",
+    "mixed_ll", "mixed_ll_reparm", "mkassert", "mkdir",
+    "mkmat", "mkspline", "ml", "ml_5", "ml_adjs", "ml_bhhhs",
+    "ml_c_d", "ml_check", "ml_clear", "ml_cnt", "ml_debug",
+    "ml_defd", "ml_e0", "ml_e0_bfgs", "ml_e0_cycle", "ml_e0_dfp",
+    "ml_e0i", "ml_e1", "ml_e1_bfgs", "ml_e1_bhhh", "ml_e1_cycle",
+    "ml_e1_dfp", "ml_e2", "ml_e2_cycle", "ml_ebfg0", "ml_ebfr0",
+    "ml_ebfr1", "ml_ebh0q", "ml_ebhh0", "ml_ebhr0", "ml_ebr0i",
+    "ml_ecr0i", "ml_edfp0", "ml_edfr0", "ml_edfr1", "ml_edr0i",
+    "ml_eds", "ml_eer0i", "ml_egr0i", "ml_elf", "ml_elf_bfgs",
+    "ml_elf_bhhh", "ml_elf_cycle", "ml_elf_dfp", "ml_elfi",
+    "ml_elfs", "ml_enr0i", "ml_enrr0", "ml_erdu0", "ml_erdu0_bfgs",
+    "ml_erdu0_bhhh", "ml_erdu0_bhhhq", "ml_erdu0_cycle",
+    "ml_erdu0_dfp", "ml_erdu0_nrbfgs", "ml_exde", "ml_footnote",
+    "ml_geqnr", "ml_grad0", "ml_graph", "ml_hbhhh", "ml_hd0",
+    "ml_hold", "ml_init", "ml_inv", "ml_log", "ml_max",
+    "ml_mlout", "ml_mlout_8", "ml_model", "ml_nb0", "ml_opt",
+    "ml_p", "ml_plot", "ml_query", "ml_rdgrd", "ml_repor",
+    "ml_s_e", "ml_score", "ml_searc", "ml_technique", "ml_unhold",
+    "mleval", "mlf_", "mlmatbysum", "mlmatsum", "mlog", "mlogi",
+    "mlogit", "mlogit_footnote", "mlogit_p", "mlopts", "mlsum",
+    "mlvecsum", "mnl0_", "mor", "more", "mov", "move", "mprobit",
+    "mprobit_lf", "mprobit_p", "mrdu0_", "mrdu1_", "mvdecode",
+    "mvencode", "mvreg", "mvreg_estat", "n", "nbreg",
+    "nbreg_al", "nbreg_lf", "nbreg_p", "nbreg_sw", "nestreg", "net",
+    "newey", "newey_7", "newey_p", "news", "nl", "nl_7", "nl_9",
+    "nl_9_p", "nl_p", "nl_p_7", "nlcom", "nlcom_p", "nlexp2",
+    "nlexp2_7", "nlexp2a", "nlexp2a_7", "nlexp3", "nlexp3_7",
+    "nlgom3", "nlgom3_7", "nlgom4", "nlgom4_7", "nlinit", "nllog3",
+    "nllog3_7", "nllog4", "nllog4_7", "nlog_rd", "nlogit",
+    "nlogit_p", "nlogitgen", "nlogittree", "nlpred", "no",
+    "nobreak", "noi", "nois", "noisi", "noisil", "noisily", "note",
+    "notes", "notes_dlg", "nptrend", "numlabel", "numlist", "odbc",
+    "old_ver", "olo", "olog", "ologi", "ologi_sw", "ologit",
+    "ologit_p", "ologitp", "on", "one", "onew", "onewa", "oneway",
+    "op_colnm", "op_comp", "op_diff", "op_inv", "op_str", "opr",
+    "opro", "oprob", "oprob_sw", "oprobi", "oprobi_p", "oprobit",
+    "oprobitp", "opts_exclusive", "order", "orthog", "orthpoly",
+    "ou", "out", "outf", "outfi", "outfil", "outfile", "outs",
+    "outsh", "outshe", "outshee", "outsheet", "ovtest", "pac",
+    "pac_7", "palette", "parse", "parse_dissim", "pause", "pca",
+    "pca_8", "pca_display", "pca_estat", "pca_p", "pca_rotate",
+    "pcamat", "pchart", "pchart_7", "pchi", "pchi_7", "pcorr",
+    "pctile", "pentium", "pergram", "pergram_7", "permute",
+    "permute_8", "personal", "peto_st", "pkcollapse", "pkcross",
+    "pkequiv", "pkexamine", "pkexamine_7", "pkshape", "pksumm",
+    "pksumm_7", "pl", "plo", "plot", "plugin", "pnorm",
+    "pnorm_7", "poisgof", "poiss_lf", "poiss_sw", "poisso_p",
+    "poisson", "poisson_estat", "post", "postclose", "postfile",
+    "postutil", "pperron", "pr", "prais", "prais_e", "prais_e2",
+    "prais_p", "predict", "predictnl", "preserve", "print",
+    "pro", "prob", "probi", "probit", "probit_estat", "probit_p",
+    "proc_time", "procoverlay", "procrustes", "procrustes_estat",
+    "procrustes_p", "profiler", "prog", "progr", "progra",
+    "program", "prop", "proportion", "prtest", "prtesti", "pwcorr",
+    "pwd", "q", "s", "qby", "qbys", "qchi", "qchi_7", "qladder",
+    "qladder_7", "qnorm", "qnorm_7", "qqplot", "qqplot_7", "qreg",
+    "qreg_c", "qreg_p", "qreg_sw", "qu", "quadchk", "quantile",
+    "quantile_7", "que", "quer", "query", "range", "ranksum",
+    "ratio", "rchart", "rchart_7", "rcof", "recast", "reclink",
+    "recode", "reg", "reg3", "reg3_p", "regdw", "regr", "regre",
+    "regre_p2", "regres", "regres_p", "regress", "regress_estat",
+    "regriv_p", "remap", "ren", "rena", "renam", "rename",
+    "renpfix", "repeat", "replace", "report", "reshape",
+    "restore", "ret", "retu", "retur", "return", "rm", "rmdir",
+    "robvar", "roccomp", "roccomp_7", "roccomp_8", "rocf_lf",
+    "rocfit", "rocfit_8", "rocgold", "rocplot", "rocplot_7",
+    "roctab", "roctab_7", "rolling", "rologit", "rologit_p",
+    "rot", "rota", "rotat", "rotate", "rotatemat", "rreg",
+    "rreg_p", "ru", "run", "runtest", "rvfplot", "rvfplot_7",
+    "rvpplot", "rvpplot_7", "sa", "safesum", "sample",
+    "sampsi", "sav", "save", "savedresults", "saveold", "sc",
+    "sca", "scal", "scala", "scalar", "scatter", "scm_mine",
+    "sco", "scob_lf", "scob_p", "scobi_sw", "scobit", "scor",
+    "score", "scoreplot", "scoreplot_help", "scree", "screeplot",
+    "screeplot_help", "sdtest", "sdtesti", "se", "search",
+    "separate", "seperate", "serrbar", "serrbar_7", "serset", "set",
+    "set_defaults", "sfrancia", "sh", "she", "shel", "shell",
+    "shewhart", "shewhart_7", "signestimationsample", "signrank",
+    "signtest", "simul", "simul_7", "simulate", "simulate_8",
+    "sktest", "sleep", "slogit", "slogit_d2", "slogit_p", "smooth",
+    "snapspan", "so", "sor", "sort", "spearman", "spikeplot",
+    "spikeplot_7", "spikeplt", "spline_x", "split", "sqreg",
+    "sqreg_p", "sret", "sretu", "sretur", "sreturn", "ssc", "st",
+    "st_ct", "st_hc", "st_hcd", "st_hcd_sh", "st_is", "st_issys",
+    "st_note", "st_promo", "st_set", "st_show", "st_smpl",
+    "st_subid", "stack", "statsby", "statsby_8", "stbase", "stci",
+    "stci_7", "stcox", "stcox_estat", "stcox_fr", "stcox_fr_ll",
+    "stcox_p", "stcox_sw", "stcoxkm", "stcoxkm_7", "stcstat",
+    "stcurv", "stcurve", "stcurve_7", "stdes", "stem", "stepwise",
+    "stereg", "stfill", "stgen", "stir", "stjoin", "stmc", "stmh",
+    "stphplot", "stphplot_7", "stphtest", "stphtest_7",
+    "stptime", "strate", "strate_7", "streg", "streg_sw", "streset",
+    "sts", "sts_7", "stset", "stsplit", "stsum", "sttocc",
+    "sttoct", "stvary", "stweib", "su", "suest", "suest_8",
+    "sum", "summ", "summa", "summar", "summari", "summariz",
+    "summarize", "sunflower", "sureg", "survcurv", "survsum",
+    "svar", "svar_p", "svmat", "svy", "svy_disp", "svy_dreg",
+    "svy_est", "svy_est_7", "svy_estat", "svy_get", "svy_gnbreg_p",
+    "svy_head", "svy_header", "svy_heckman_p", "svy_heckprob_p",
+    "svy_intreg_p", "svy_ivreg_p", "svy_logistic_p", "svy_logit_p",
+    "svy_mlogit_p", "svy_nbreg_p", "svy_ologit_p", "svy_oprobit_p",
+    "svy_poisson_p", "svy_probit_p", "svy_regress_p", "svy_sub",
+    "svy_sub_7", "svy_x", "svy_x_7", "svy_x_p", "svydes",
+    "svydes_8", "svygen", "svygnbreg", "svyheckman", "svyheckprob",
+    "svyintreg", "svyintreg_7", "svyintrg", "svyivreg", "svylc",
+    "svylog_p", "svylogit", "svymarkout", "svymarkout_8",
+    "svymean", "svymlog", "svymlogit", "svynbreg", "svyolog",
+    "svyologit", "svyoprob", "svyoprobit", "svyopts",
+    "svypois", "svypois_7", "svypoisson", "svyprobit", "svyprobt",
+    "svyprop", "svyprop_7", "svyratio", "svyreg", "svyreg_p",
+    "svyregress", "svyset", "svyset_7", "svyset_8", "svytab",
+    "svytab_7", "svytest", "svytotal", "sw", "sw_8", "swcnreg",
+    "swcox", "swereg", "swilk", "swlogis", "swlogit",
+    "swologit", "swoprbt", "swpois", "swprobit", "swqreg",
+    "swtobit", "swweib", "symmetry", "symmi", "symplot",
+    "symplot_7", "syntax", "sysdescribe", "sysdir", "sysuse",
+    "szroeter", "ta", "tab", "tab1", "tab2", "tab_or", "tabd",
+    "tabdi", "tabdis", "tabdisp", "tabi", "table", "tabodds",
+    "tabodds_7", "tabstat", "tabu", "tabul", "tabula", "tabulat",
+    "tabulate", "te", "tempfile", "tempname", "tempvar", "tes",
+    "test", "testnl", "testparm", "teststd", "tetrachoric",
+    "time_it", "timer", "tis", "tob", "tobi", "tobit", "tobit_p",
+    "tobit_sw", "token", "tokeni", "tokeniz", "tokenize",
+    "tostring", "total", "translate", "translator", "transmap",
+    "treat_ll", "treatr_p", "treatreg", "trim", "trnb_cons",
+    "trnb_mean", "trpoiss_d2", "trunc_ll", "truncr_p", "truncreg",
+    "tsappend", "tset", "tsfill", "tsline", "tsline_ex",
+    "tsreport", "tsrevar", "tsrline", "tsset", "tssmooth",
+    "tsunab", "ttest", "ttesti", "tut_chk", "tut_wait", "tutorial",
+    "tw", "tware_st", "two", "twoway", "twoway__fpfit_serset",
+    "twoway__function_gen", "twoway__histogram_gen",
+    "twoway__ipoint_serset", "twoway__ipoints_serset",
+    "twoway__kdensity_gen", "twoway__lfit_serset",
+    "twoway__normgen_gen", "twoway__pci_serset",
+    "twoway__qfit_serset", "twoway__scatteri_serset",
+    "twoway__sunflower_gen", "twoway_ksm_serset", "ty", "typ",
+    "type", "typeof", "u", "unab", "unabbrev", "unabcmd",
+    "update", "us", "use", "uselabel", "var", "var_mkcompanion",
+    "var_p", "varbasic", "varfcast", "vargranger", "varirf",
+    "varirf_add", "varirf_cgraph", "varirf_create", "varirf_ctable",
+    "varirf_describe", "varirf_dir", "varirf_drop", "varirf_erase",
+    "varirf_graph", "varirf_ograph", "varirf_rename", "varirf_set",
+    "varirf_table", "varlist", "varlmar", "varnorm", "varsoc",
+    "varstable", "varstable_w", "varstable_w2", "varwle",
+    "vce", "vec", "vec_fevd", "vec_mkphi", "vec_p", "vec_p_w",
+    "vecirf_create", "veclmar", "veclmar_w", "vecnorm",
+    "vecnorm_w", "vecrank", "vecstable", "verinst", "vers",
+    "versi", "versio", "version", "view", "viewsource", "vif",
+    "vwls", "wdatetof", "webdescribe", "webseek", "webuse",
+    "weib1_lf", "weib2_lf", "weib_lf", "weib_lf0", "weibhet_glf",
+    "weibhet_glf_sh", "weibhet_glfa", "weibhet_glfa_sh",
+    "weibhet_gp", "weibhet_ilf", "weibhet_ilf_sh", "weibhet_ilfa",
+    "weibhet_ilfa_sh", "weibhet_ip", "weibu_sw", "weibul_p",
+    "weibull", "weibull_c", "weibull_s", "weibullhet",
+    "wh", "whelp", "whi", "which", "whil", "while", "wilc_st",
+    "wilcoxon", "win", "wind", "windo", "window", "winexec",
+    "wntestb", "wntestb_7", "wntestq", "xchart", "xchart_7",
+    "xcorr", "xcorr_7", "xi", "xi_6", "xmlsav", "xmlsave",
+    "xmluse", "xpose", "xsh", "xshe", "xshel", "xshell",
+    "xt_iis", "xt_tis", "xtab_p", "xtabond", "xtbin_p",
+    "xtclog", "xtcloglog", "xtcloglog_8", "xtcloglog_d2",
+    "xtcloglog_pa_p", "xtcloglog_re_p", "xtcnt_p", "xtcorr",
+    "xtdata", "xtdes", "xtfront_p", "xtfrontier", "xtgee",
+    "xtgee_elink", "xtgee_estat", "xtgee_makeivar", "xtgee_p",
+    "xtgee_plink", "xtgls", "xtgls_p", "xthaus", "xthausman",
+    "xtht_p", "xthtaylor", "xtile", "xtint_p", "xtintreg",
+    "xtintreg_8", "xtintreg_d2", "xtintreg_p", "xtivp_1",
+    "xtivp_2", "xtivreg", "xtline", "xtline_ex", "xtlogit",
+    "xtlogit_8", "xtlogit_d2", "xtlogit_fe_p", "xtlogit_pa_p",
+    "xtlogit_re_p", "xtmixed", "xtmixed_estat", "xtmixed_p",
+    "xtnb_fe", "xtnb_lf", "xtnbreg", "xtnbreg_pa_p",
+    "xtnbreg_refe_p", "xtpcse", "xtpcse_p", "xtpois", "xtpoisson",
+    "xtpoisson_d2", "xtpoisson_pa_p", "xtpoisson_refe_p", "xtpred",
+    "xtprobit", "xtprobit_8", "xtprobit_d2", "xtprobit_re_p",
+    "xtps_fe", "xtps_lf", "xtps_ren", "xtps_ren_8", "xtrar_p",
+    "xtrc", "xtrc_p", "xtrchh", "xtrefe_p", "xtreg", "xtreg_be",
+    "xtreg_fe", "xtreg_ml", "xtreg_pa_p", "xtreg_re",
+    "xtregar", "xtrere_p", "xtset", "xtsf_ll", "xtsf_llti",
+    "xtsum", "xttab", "xttest0", "xttobit", "xttobit_8",
+    "xttobit_p", "xttrans", "yx", "yxview__barlike_draw",
+    "yxview_area_draw", "yxview_bar_draw", "yxview_dot_draw",
+    "yxview_dropline_draw", "yxview_function_draw",
+    "yxview_iarrow_draw", "yxview_ilabels_draw",
+    "yxview_normal_draw", "yxview_pcarrow_draw",
+    "yxview_pcbarrow_draw", "yxview_pccapsym_draw",
+    "yxview_pcscatter_draw", "yxview_pcspike_draw",
+    "yxview_rarea_draw", "yxview_rbar_draw", "yxview_rbarm_draw",
+    "yxview_rcap_draw", "yxview_rcapsym_draw",
+    "yxview_rconnected_draw", "yxview_rline_draw",
+    "yxview_rscatter_draw", "yxview_rspike_draw",
+    "yxview_spike_draw", "yxview_sunflower_draw", "zap_s", "zinb",
+    "zinb_llf", "zinb_plf", "zip", "zip_llf", "zip_p", "zip_plf",
+    "zt_ct_5", "zt_hc_5", "zt_hcd_5", "zt_is_5", "zt_iss_5",
+    "zt_sho_5", "zt_smp_5", "ztbase_5", "ztcox_5", "ztdes_5",
+    "ztereg_5", "ztfill_5", "ztgen_5", "ztir_5", "ztjoin_5", "ztnb",
+    "ztnb_p", "ztp", "ztp_p", "zts_5", "ztset_5", "ztspli_5",
+    "ztsum_5", "zttoct_5", "ztvary_5", "ztweib_5"
+)
+
+builtins_functions = (
+    "Cdhms", "Chms", "Clock", "Cmdyhms", "Cofc", "Cofd", "F",
+    "Fden", "Ftail", "I", "J", "_caller", "abbrev", "abs", "acos",
+    "acosh", "asin", "asinh", "atan", "atan2", "atanh",
+    "autocode", "betaden", "binomial", "binomialp", "binomialtail",
+    "binormal", "bofd", "byteorder", "c", "ceil", "char",
+    "chi2", "chi2den", "chi2tail", "cholesky", "chop", "clip",
+    "clock", "cloglog", "cofC", "cofd", "colnumb", "colsof", "comb",
+    "cond", "corr", "cos", "cosh", "d", "daily", "date", "day",
+    "det", "dgammapda", "dgammapdada", "dgammapdadx", "dgammapdx",
+    "dgammapdxdx", "dhms", "diag", "diag0cnt", "digamma",
+    "dofC", "dofb", "dofc", "dofh", "dofm", "dofq", "dofw",
+    "dofy", "dow", "doy", "dunnettprob", "e", "el", "epsdouble",
+    "epsfloat", "exp", "fileexists", "fileread", "filereaderror",
+    "filewrite", "float", "floor", "fmtwidth", "gammaden",
+    "gammap", "gammaptail", "get", "group", "h", "hadamard",
+    "halfyear", "halfyearly", "has_eprop", "hh", "hhC", "hms",
+    "hofd", "hours", "hypergeometric", "hypergeometricp", "ibeta",
+    "ibetatail", "index", "indexnot", "inlist", "inrange", "int",
+    "inv", "invF", "invFtail", "invbinomial", "invbinomialtail",
+    "invchi2", "invchi2tail", "invcloglog", "invdunnettprob",
+    "invgammap", "invgammaptail", "invibeta", "invibetatail",
+    "invlogit", "invnFtail", "invnbinomial", "invnbinomialtail",
+    "invnchi2", "invnchi2tail", "invnibeta", "invnorm", "invnormal",
+    "invnttail", "invpoisson", "invpoissontail", "invsym", "invt",
+    "invttail", "invtukeyprob", "irecode", "issym", "issymmetric",
+    "itrim", "length", "ln", "lnfact", "lnfactorial", "lngamma",
+    "lnnormal", "lnnormalden", "log", "log10", "logit", "lower",
+    "ltrim", "m", "match", "matmissing", "matrix", "matuniform",
+    "max", "maxbyte", "maxdouble", "maxfloat", "maxint", "maxlong",
+    "mdy", "mdyhms", "mi", "min", "minbyte", "mindouble",
+    "minfloat", "minint", "minlong", "minutes", "missing", "mm",
+    "mmC", "mod", "mofd", "month", "monthly", "mreldif",
+    "msofhours", "msofminutes", "msofseconds", "nF", "nFden",
+    "nFtail", "nbetaden", "nbinomial", "nbinomialp", "nbinomialtail",
+    "nchi2", "nchi2den", "nchi2tail", "nibeta", "norm", "normal",
+    "normalden", "normd", "npnF", "npnchi2", "npnt", "nt", "ntden",
+    "nttail", "nullmat", "plural", "poisson", "poissonp",
+    "poissontail", "proper", "q", "qofd", "quarter", "quarterly",
+    "r", "rbeta", "rbinomial", "rchi2", "real", "recode", "regexm",
+    "regexr", "regexs", "reldif", "replay", "return", "reverse",
+    "rgamma", "rhypergeometric", "rnbinomial", "rnormal", "round",
+    "rownumb", "rowsof", "rpoisson", "rt", "rtrim", "runiform", "s",
+    "scalar", "seconds", "sign", "sin", "sinh", "smallestdouble",
+    "soundex", "soundex_nara", "sqrt", "ss", "ssC", "strcat",
+    "strdup", "string", "strlen", "strlower", "strltrim", "strmatch",
+    "strofreal", "strpos", "strproper", "strreverse", "strrtrim",
+    "strtoname", "strtrim", "strupper", "subinstr", "subinword",
+    "substr", "sum", "sweep", "syminv", "t", "tC", "tan", "tanh",
+    "tc", "td", "tden", "th", "tin", "tm", "tq", "trace",
+    "trigamma", "trim", "trunc", "ttail", "tukeyprob", "tw",
+    "twithin", "uniform", "upper", "vec", "vecdiag", "w", "week",
+    "weekly", "wofd", "word", "wordcount", "year", "yearly",
+    "yh", "ym", "yofd", "yq", "yw"
+)
diff --git a/pygments/lexers/stata.py b/pygments/lexers/stata.py
index fd63db4a..3aad1ea9 100644
--- a/pygments/lexers/stata.py
+++ b/pygments/lexers/stata.py
@@ -1,487 +1,152 @@
 # -*- coding: utf-8 -*-
-
+# yapf: disable
 """
     pygments.lexers.stata
     ~~~~~~~~~~~~~~~~~~~~~
 
     Lexer for Stata
+
+    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
 """
 
+import re
 from pygments.lexer import RegexLexer, include, words
 from pygments.token import Comment, Keyword, Name, Number, \
     String, Text, Operator
 
+from pygments.lexers._stata_builtins import builtins_base, builtins_functions
+
 __all__ = ['StataLexer']
 
+
 class StataLexer(RegexLexer):
     """
-    For `Stata <http://www.stata.com/>` do files.
+    For `Stata <http://www.stata.com/>`_ do files.
 
-    Syntax from
-    - http://fmwww.bc.edu/RePEc/bocode/s/synlightlist.ado
-    - github.com/isagalaev/highlight.js/blob/master/src/languages/stata.js
-    - github.com/jpitblado/vim-stata/blob/master/syntax/stata.vim
+    .. versionadded:: 2.2
     """
+    # Syntax based on
+    # - http://fmwww.bc.edu/RePEc/bocode/s/synlightlist.ado
+    # - http://github.com/isagalaev/highlight.js/blob/master/src/languages/stata.js
+    # - http://github.com/jpitblado/vim-stata/blob/master/syntax/stata.vim
 
-    name      = 'Stata'
-    aliases   = ['stata', 'do', 'Stata']
+    name = 'Stata'
+    aliases = ['stata', 'do']
     filenames = ['*.do', '*.ado']
     mimetypes = ['text/x-stata', 'text/stata', 'application/x-stata']
-
-    builtins_base = (
-        "if", "else", "in", "foreach", "for", "forv", "forva",
-        "forval", "forvalu", "forvalue", "forvalues", "by", "bys",
-        "bysort", "xi", "quietly", "qui", "capture", "about", "ac",
-        "ac_7", "acprplot", "acprplot_7 adjust", "ado", "adopath",
-        "adoupdate", "alpha", "ameans", "an", "ano", "anov", "anova",
-        "anova_estat", "anova_terms", "anovadef", "aorder", "ap", "app",
-        "appe", "appen", "append", "arch", "arch_dr", "arch_estat",
-        "arch_p", "archlm", "areg", "areg_p", "args", "arima",
-        "arima_dr", "arima_estat", "arima_p", "as", "asmprobit",
-        "asmprobit_estat", "asmprobit_lf", "asmprobit_mfx__dlg",
-        "asmprobit_p", "ass", "asse", "asser", "assert", "avplot",
-        "avplot_7", "avplots", "avplots_7 bcskew0", "bgodfrey",
-        "binreg", "bip0_lf", "biplot", "bipp_lf", "bipr_lf",
-        "bipr_p", "biprobit", "bitest", "bitesti", "bitowt", "blogit",
-        "bmemsize", "boot", "bootsamp", "bootstrap", "bootstrap_8",
-        "boxco_l", "boxco_p", "boxcox", "boxcox_6", "boxcox_p",
-        "bprobit", "br", "break", "brier", "bro", "brow", "brows",
-        "browse", "brr", "brrstat", "bs", "bs_7", "bsampl_w",
-        "bsample", "bsample_7", "bsqreg", "bstat", "bstat_7", "bstat_8",
-        "bstrap", "bstrap_7", "ca", "ca_estat", "ca_p", "cabiplot",
-        "camat", "canon", "canon_8", "canon_8_p", "canon_estat",
-        "canon_p", "cap", "caprojection", "capt", "captu", "captur",
-        "capture", "cat", "cc", "cchart", "cchart_7", "cci",
-        "cd", "censobs_table", "centile", "cf", "char", "chdir",
-        "checkdlgfiles", "checkestimationsample", "checkhlpfiles",
-        "checksum", "chelp", "ci", "cii", "cl", "class", "classutil",
-        "clear", "cli", "clis", "clist", "clo", "clog", "clog_lf",
-        "clog_p", "clogi", "clogi_sw", "clogit", "clogit_lf",
-        "clogit_p", "clogitp", "clogl_sw", "cloglog", "clonevar",
-        "clslistarray", "cluster", "cluster_measures", "cluster_stop",
-        "cluster_tree", "cluster_tree_8", "clustermat", "cmdlog",
-        "cnr", "cnre", "cnreg", "cnreg_p", "cnreg_sw", "cnsreg",
-        "codebook", "collaps4", "collapse", "colormult_nb",
-        "colormult_nw", "compare", "compress", "conf", "confi",
-        "confir", "confirm", "conren", "cons", "const", "constr",
-        "constra", "constrai", "constrain", "constraint", "continue",
-        "contract", "copy", "copyright", "copysource", "cor", "corc",
-        "corr", "corr2data", "corr_anti", "corr_kmo", "corr_smc",
-        "corre", "correl", "correla", "correlat", "correlate",
-        "corrgram", "cou", "coun", "count", "cox", "cox_p", "cox_sw",
-        "coxbase", "coxhaz", "coxvar", "cprplot", "cprplot_7",
-        "crc", "cret", "cretu", "cretur", "creturn", "cross", "cs",
-        "cscript", "cscript_log", "csi", "ct", "ct_is", "ctset",
-        "ctst_5", "ctst_st", "cttost", "cumsp", "cumsp_7", "cumul",
-        "cusum", "cusum_7", "cutil", "d", "datasig", "datasign",
-        "datasigna", "datasignat", "datasignatu", "datasignatur",
-        "datasignature", "datetof", "db", "dbeta", "de", "dec",
-        "deco", "decod", "decode", "deff", "des", "desc", "descr",
-        "descri", "describ", "describe", "destring", "dfbeta",
-        "dfgls", "dfuller", "di", "di_g", "dir", "dirstats", "dis",
-        "discard", "disp", "disp_res", "disp_s", "displ", "displa",
-        "display", "distinct", "do", "doe", "doed", "doedi",
-        "doedit", "dotplot", "dotplot_7", "dprobit", "drawnorm",
-        "drop", "ds", "ds_util", "dstdize", "duplicates", "durbina",
-        "dwstat", "dydx", "e", "ed", "edi", "edit", "egen",
-        "eivreg", "emdef", "en", "enc", "enco", "encod", "encode",
-        "eq", "erase", "ereg", "ereg_lf", "ereg_p", "ereg_sw",
-        "ereghet", "ereghet_glf", "ereghet_glf_sh", "ereghet_gp",
-        "ereghet_ilf", "ereghet_ilf_sh", "ereghet_ip", "eret",
-        "eretu", "eretur", "ereturn", "err", "erro", "error", "est",
-        "est_cfexist", "est_cfname", "est_clickable", "est_expand",
-        "est_hold", "est_table", "est_unhold", "est_unholdok",
-        "estat", "estat_default", "estat_summ", "estat_vce_only",
-        "esti", "estimates", "etodow", "etof", "etomdy", "ex",
-        "exi", "exit", "expand", "expandcl", "fac", "fact", "facto",
-        "factor", "factor_estat", "factor_p", "factor_pca_rotated",
-        "factor_rotate", "factormat", "fcast", "fcast_compute",
-        "fcast_graph", "fdades", "fdadesc", "fdadescr", "fdadescri",
-        "fdadescrib", "fdadescribe", "fdasav", "fdasave", "fdause",
-        "fh_st", "file", "open", "file", "read", "file", "close",
-        "file", "filefilter", "fillin", "find_hlp_file", "findfile",
-        "findit", "findit_7", "fit", "fl", "fli", "flis", "flist",
-        "for5_0", "form", "forma", "format", "fpredict", "frac_154",
-        "frac_adj", "frac_chk", "frac_cox", "frac_ddp", "frac_dis",
-        "frac_dv", "frac_in", "frac_mun", "frac_pp", "frac_pq",
-        "frac_pv", "frac_wgt", "frac_xo", "fracgen", "fracplot",
-        "fracplot_7", "fracpoly", "fracpred", "fron_ex", "fron_hn",
-        "fron_p", "fron_tn", "fron_tn2", "frontier", "ftodate", "ftoe",
-        "ftomdy", "ftowdate", "g", "gamhet_glf", "gamhet_gp",
-        "gamhet_ilf", "gamhet_ip", "gamma", "gamma_d2", "gamma_p",
-        "gamma_sw", "gammahet", "gdi_hexagon", "gdi_spokes", "ge",
-        "gen", "gene", "gener", "genera", "generat", "generate",
-        "genrank", "genstd", "genvmean", "gettoken", "gl", "gladder",
-        "gladder_7", "glim_l01", "glim_l02 glim_l03", "glim_l04",
-        "glim_l05", "glim_l06", "glim_l07", "glim_l08", "glim_l09",
-        "glim_l10 glim_l11", "glim_l12", "glim_lf", "glim_mu",
-        "glim_nw1", "glim_nw2", "glim_nw3", "glim_p", "glim_v1",
-        "glim_v2", "glim_v3", "glim_v4", "glim_v5", "glim_v6",
-        "glim_v7", "glm", "glm_6 glm_p", "glm_sw", "glmpred", "glo",
-        "glob", "globa", "global", "glogit", "glogit_8", "glogit_p",
-        "gmeans", "gnbre_lf", "gnbreg", "gnbreg_5", "gnbreg_p",
-        "gomp_lf", "gompe_sw", "gomper_p", "gompertz", "gompertzhet",
-        "gomphet_glf", "gomphet_glf_sh", "gomphet_gp", "gomphet_ilf",
-        "gomphet_ilf_sh", "gomphet_ip", "gphdot", "gphpen",
-        "gphprint", "gprefs", "gprobi_p", "gprobit", "gprobit_8", "gr",
-        "gr7", "gr_copy", "gr_current", "gr_db", "gr_describe",
-        "gr_dir", "gr_draw", "gr_draw_replay", "gr_drop", "gr_edit",
-        "gr_editviewopts", "gr_example", "gr_example2 gr_export",
-        "gr_print", "gr_qscheme", "gr_query", "gr_read", "gr_rename",
-        "gr_replay", "gr_save", "gr_set", "gr_setscheme", "gr_table",
-        "gr_undo", "gr_use", "graph", "graph7 grebar", "greigen",
-        "greigen_7", "greigen_8", "grmeanby", "grmeanby_7",
-        "gs_fileinfo", "gs_filetype", "gs_graphinfo", "gs_stat",
-        "gsort", "gwood", "h", "hadimvo", "hareg", "hausman",
-        "haver", "he", "heck_d2", "heckma_p", "heckman", "heckp_lf",
-        "heckpr_p", "heckprob", "hel", "help", "hereg", "hetpr_lf",
-        "hetpr_p", "hetprob", "hettest", "hexdump", "hilite",
-        "hist", "hist_7 histogram", "hlogit", "hlu", "hmeans",
-        "hotel", "hotelling", "hprobit", "hreg", "hsearch", "icd9",
-        "icd9_ff", "icd9p", "iis", "impute", "imtest", "inbase",
-        "include", "inf", "infi", "infil", "infile", "infix", "inp",
-        "inpu", "input", "ins", "insheet", "insp", "inspe",
-        "inspec", "inspect", "integ", "inten", "intreg", "intreg_7",
-        "intreg_p", "intrg2_ll", "intrg_ll", "intrg_ll2", "ipolate",
-        "iqreg", "ir", "irf", "irf_create", "irfm", "iri", "is_svy",
-        "is_svysum", "isid", "istdize", "ivprob_1_lf", "ivprob_lf",
-        "ivprobit", "ivprobit_p", "ivreg", "ivreg_footnote",
-        "ivtob_1_lf", "ivtob_lf", "ivtobit", "ivtobit_p", "jackknife",
-        "jacknife", "jknife", "jknife_6", "jknife_8", "jkstat",
-        "joinby", "kalarma1", "kap", "kap_3", "kapmeier", "kappa",
-        "kapwgt", "kdensity", "kdensity_7 keep", "ksm", "ksmirnov",
-        "ktau", "kwallis", "l", "la", "lab", "labe", "label",
-        "labelbook", "ladder", "levels", "levelsof", "leverage",
-        "lfit", "lfit_p", "li", "lincom", "line", "linktest",
-        "lis", "list", "lloghet_glf", "lloghet_glf_sh", "lloghet_gp",
-        "lloghet_ilf", "lloghet_ilf_sh", "lloghet_ip", "llogi_sw",
-        "llogis_p", "llogist", "llogistic", "llogistichet",
-        "lnorm_lf", "lnorm_sw", "lnorma_p", "lnormal", "lnormalhet",
-        "lnormhet_glf", "lnormhet_glf_sh", "lnormhet_gp",
-        "lnormhet_ilf", "lnormhet_ilf_sh", "lnormhet_ip", "lnskew0",
-        "loadingplot", "loc", "loca", "local", "log", "logi",
-        "logis_lf", "logistic", "logistic_p", "logit", "logit_estat",
-        "logit_p", "loglogs", "logrank", "loneway", "lookfor",
-        "lookup", "lowess", "lowess_7", "lpredict", "lrecomp", "lroc",
-        "lroc_7", "lrtest", "ls", "lsens", "lsens_7", "lsens_x",
-        "lstat", "ltable", "ltable_7", "ltriang", "lv", "lvr2plot",
-        "lvr2plot_7", "m", "ma", "mac", "macr", "macro", "makecns",
-        "man", "manova", "manova_estat", "manova_p", "manovatest",
-        "mantel", "mark", "markin", "markout", "marksample", "mat",
-        "mat_capp", "mat_order", "mat_put_rr", "mat_rapp", "mata",
-        "mata_clear", "mata_describe", "mata_drop", "mata_matdescribe",
-        "mata_matsave", "mata_matuse", "mata_memory", "mata_mlib",
-        "mata_mosave", "mata_rename", "mata_which", "matalabel",
-        "matcproc", "matlist", "matname", "matr", "matri",
-        "matrix", "matrix_input__dlg", "matstrik", "mcc", "mcci",
-        "md0_", "md1_", "md1debug_", "md2_", "md2debug_", "mds",
-        "mds_estat", "mds_p", "mdsconfig", "mdslong", "mdsmat",
-        "mdsshepard", "mdytoe", "mdytof", "me_derd", "mean",
-        "means", "median", "memory", "memsize", "meqparse", "mer",
-        "merg", "merge", "mfp", "mfx", "mhelp", "mhodds", "minbound",
-        "mixed_ll", "mixed_ll_reparm", "mkassert", "mkdir",
-        "mkmat", "mkspline", "ml", "ml_5 ml_adjs", "ml_bhhhs",
-        "ml_c_d", "ml_check", "ml_clear", "ml_cnt", "ml_debug",
-        "ml_defd", "ml_e0 ml_e0_bfgs", "ml_e0_cycle", "ml_e0_dfp",
-        "ml_e0i", "ml_e1", "ml_e1_bfgs", "ml_e1_bhhh", "ml_e1_cycle",
-        "ml_e1_dfp", "ml_e2", "ml_e2_cycle", "ml_ebfg0", "ml_ebfr0",
-        "ml_ebfr1 ml_ebh0q", "ml_ebhh0", "ml_ebhr0", "ml_ebr0i",
-        "ml_ecr0i", "ml_edfp0", "ml_edfr0", "ml_edfr1 ml_edr0i",
-        "ml_eds", "ml_eer0i", "ml_egr0i", "ml_elf", "ml_elf_bfgs",
-        "ml_elf_bhhh", "ml_elf_cycle", "ml_elf_dfp", "ml_elfi",
-        "ml_elfs", "ml_enr0i", "ml_enrr0", "ml_erdu0 ml_erdu0_bfgs",
-        "ml_erdu0_bhhh", "ml_erdu0_bhhhq", "ml_erdu0_cycle",
-        "ml_erdu0_dfp", "ml_erdu0_nrbfgs", "ml_exde", "ml_footnote",
-        "ml_geqnr", "ml_grad0", "ml_graph", "ml_hbhhh", "ml_hd0",
-        "ml_hold", "ml_init", "ml_inv", "ml_log", "ml_max",
-        "ml_mlout", "ml_mlout_8", "ml_model", "ml_nb0", "ml_opt",
-        "ml_p", "ml_plot", "ml_query", "ml_rdgrd", "ml_repor",
-        "ml_s_e", "ml_score", "ml_searc", "ml_technique", "ml_unhold",
-        "mleval", "mlf_", "mlmatbysum", "mlmatsum", "mlog", "mlogi",
-        "mlogit", "mlogit_footnote", "mlogit_p", "mlopts", "mlsum",
-        "mlvecsum", "mnl0_", "mor", "more", "mov", "move", "mprobit",
-        "mprobit_lf", "mprobit_p", "mrdu0_", "mrdu1_", "mvdecode",
-        "mvencode", "mvreg", "mvreg_estat", "n", "nbreg",
-        "nbreg_al", "nbreg_lf", "nbreg_p", "nbreg_sw", "nestreg", "net",
-        "newey", "newey_7", "newey_p", "news", "nl", "nl_7", "nl_9",
-        "nl_9_p", "nl_p", "nl_p_7 nlcom", "nlcom_p", "nlexp2",
-        "nlexp2_7", "nlexp2a", "nlexp2a_7", "nlexp3", "nlexp3_7",
-        "nlgom3 nlgom3_7", "nlgom4", "nlgom4_7", "nlinit", "nllog3",
-        "nllog3_7", "nllog4", "nllog4_7", "nlog_rd", "nlogit",
-        "nlogit_p", "nlogitgen", "nlogittree", "nlpred", "no",
-        "nobreak", "noi", "nois", "noisi", "noisil", "noisily", "note",
-        "notes", "notes_dlg", "nptrend", "numlabel", "numlist", "odbc",
-        "old_ver", "olo", "olog", "ologi", "ologi_sw", "ologit",
-        "ologit_p", "ologitp", "on", "one", "onew", "onewa", "oneway",
-        "op_colnm", "op_comp", "op_diff", "op_inv", "op_str", "opr",
-        "opro", "oprob", "oprob_sw", "oprobi", "oprobi_p", "oprobit",
-        "oprobitp", "opts_exclusive", "order", "orthog", "orthpoly",
-        "ou", "out", "outf", "outfi", "outfil", "outfile", "outs",
-        "outsh", "outshe", "outshee", "outsheet", "ovtest", "pac",
-        "pac_7", "palette", "parse", "parse_dissim", "pause", "pca",
-        "pca_8 pca_display", "pca_estat", "pca_p", "pca_rotate",
-        "pcamat", "pchart", "pchart_7", "pchi", "pchi_7", "pcorr",
-        "pctile", "pentium", "pergram", "pergram_7", "permute",
-        "permute_8", "personal", "peto_st", "pkcollapse", "pkcross",
-        "pkequiv", "pkexamine", "pkexamine_7", "pkshape", "pksumm",
-        "pksumm_7", "pl", "plo", "plot", "plugin", "pnorm",
-        "pnorm_7", "poisgof", "poiss_lf", "poiss_sw", "poisso_p",
-        "poisson", "poisson_estat", "post", "postclose", "postfile",
-        "postutil", "pperron", "pr", "prais", "prais_e", "prais_e2",
-        "prais_p", "predict", "predictnl", "preserve", "print",
-        "pro", "prob", "probi", "probit", "probit_estat", "probit_p",
-        "proc_time", "procoverlay", "procrustes", "procrustes_estat",
-        "procrustes_p", "profiler", "prog", "progr", "progra",
-        "program", "prop", "proportion", "prtest", "prtesti", "pwcorr",
-        "pwd", "q", "s", "qby", "qbys", "qchi", "qchi_7", "qladder",
-        "qladder_7", "qnorm", "qnorm_7", "qqplot", "qqplot_7", "qreg",
-        "qreg_c", "qreg_p", "qreg_sw", "qu", "quadchk", "quantile",
-        "quantile_7", "que", "quer", "query", "range", "ranksum",
-        "ratio", "rchart", "rchart_7", "rcof", "recast", "reclink",
-        "recode", "reg", "reg3", "reg3_p", "regdw", "regr", "regre",
-        "regre_p2", "regres", "regres_p", "regress", "regress_estat",
-        "regriv_p", "remap", "ren", "rena", "renam", "rename",
-        "renpfix", "repeat", "replace", "report", "reshape",
-        "restore", "ret", "retu", "retur", "return", "rm", "rmdir",
-        "robvar", "roccomp", "roccomp_7", "roccomp_8", "rocf_lf",
-        "rocfit", "rocfit_8", "rocgold", "rocplot", "rocplot_7",
-        "roctab", "roctab_7", "rolling", "rologit", "rologit_p",
-        "rot", "rota", "rotat", "rotate", "rotatemat", "rreg",
-        "rreg_p", "ru", "run", "runtest", "rvfplot", "rvfplot_7",
-        "rvpplot", "rvpplot_7", "sa", "safesum", "sample",
-        "sampsi", "sav", "save", "savedresults", "saveold", "sc",
-        "sca", "scal", "scala", "scalar", "scatter", "scm_mine",
-        "sco", "scob_lf", "scob_p", "scobi_sw", "scobit", "scor",
-        "score", "scoreplot", "scoreplot_help", "scree", "screeplot",
-        "screeplot_help", "sdtest", "sdtesti", "se", "search",
-        "separate", "seperate", "serrbar", "serrbar_7", "serset", "set",
-        "set_defaults", "sfrancia", "sh", "she", "shel", "shell",
-        "shewhart", "shewhart_7", "signestimationsample", "signrank",
-        "signtest", "simul", "simul_7 simulate", "simulate_8",
-        "sktest", "sleep", "slogit", "slogit_d2", "slogit_p", "smooth",
-        "snapspan", "so", "sor", "sort", "spearman", "spikeplot",
-        "spikeplot_7", "spikeplt", "spline_x", "split", "sqreg",
-        "sqreg_p", "sret", "sretu", "sretur", "sreturn", "ssc", "st",
-        "st_ct", "st_hc", "st_hcd", "st_hcd_sh", "st_is", "st_issys",
-        "st_note", "st_promo", "st_set", "st_show", "st_smpl",
-        "st_subid", "stack", "statsby", "statsby_8", "stbase", "stci",
-        "stci_7", "stcox", "stcox_estat", "stcox_fr", "stcox_fr_ll",
-        "stcox_p", "stcox_sw", "stcoxkm", "stcoxkm_7", "stcstat",
-        "stcurv", "stcurve", "stcurve_7", "stdes", "stem", "stepwise",
-        "stereg", "stfill", "stgen", "stir", "stjoin", "stmc", "stmh",
-        "stphplot", "stphplot_7", "stphtest", "stphtest_7",
-        "stptime", "strate", "strate_7", "streg", "streg_sw", "streset",
-        "sts", "sts_7", "stset", "stsplit", "stsum", "sttocc",
-        "sttoct", "stvary", "stweib", "su", "suest", "suest_8",
-        "sum", "summ", "summa", "summar", "summari", "summariz",
-        "summarize", "sunflower", "sureg", "survcurv", "survsum",
-        "svar", "svar_p", "svmat", "svy", "svy_disp", "svy_dreg",
-        "svy_est", "svy_est_7", "svy_estat", "svy_get", "svy_gnbreg_p",
-        "svy_head", "svy_header", "svy_heckman_p", "svy_heckprob_p",
-        "svy_intreg_p", "svy_ivreg_p", "svy_logistic_p", "svy_logit_p",
-        "svy_mlogit_p", "svy_nbreg_p", "svy_ologit_p", "svy_oprobit_p",
-        "svy_poisson_p", "svy_probit_p", "svy_regress_p", "svy_sub",
-        "svy_sub_7", "svy_x", "svy_x_7", "svy_x_p", "svydes",
-        "svydes_8", "svygen", "svygnbreg", "svyheckman", "svyheckprob",
-        "svyintreg", "svyintreg_7", "svyintrg", "svyivreg", "svylc",
-        "svylog_p", "svylogit", "svymarkout", "svymarkout_8",
-        "svymean", "svymlog", "svymlogit", "svynbreg", "svyolog",
-        "svyologit", "svyoprob", "svyoprobit", "svyopts",
-        "svypois", "svypois_7 svypoisson", "svyprobit", "svyprobt",
-        "svyprop", "svyprop_7", "svyratio", "svyreg", "svyreg_p",
-        "svyregress", "svyset", "svyset_7", "svyset_8", "svytab",
-        "svytab_7", "svytest", "svytotal", "sw", "sw_8", "swcnreg",
-        "swcox", "swereg", "swilk", "swlogis", "swlogit",
-        "swologit", "swoprbt", "swpois", "swprobit", "swqreg",
-        "swtobit", "swweib", "symmetry", "symmi", "symplot",
-        "symplot_7 syntax", "sysdescribe", "sysdir", "sysuse",
-        "szroeter", "ta", "tab", "tab1", "tab2", "tab_or", "tabd",
-        "tabdi", "tabdis", "tabdisp", "tabi", "table", "tabodds",
-        "tabodds_7", "tabstat", "tabu", "tabul", "tabula", "tabulat",
-        "tabulate", "te", "tempfile", "tempname", "tempvar", "tes",
-        "test", "testnl", "testparm", "teststd", "tetrachoric",
-        "time_it", "timer", "tis", "tob", "tobi", "tobit", "tobit_p",
-        "tobit_sw", "token", "tokeni", "tokeniz", "tokenize",
-        "tostring", "total", "translate", "translator", "transmap",
-        "treat_ll", "treatr_p", "treatreg", "trim", "trnb_cons",
-        "trnb_mean", "trpoiss_d2", "trunc_ll", "truncr_p", "truncreg",
-        "tsappend", "tset", "tsfill", "tsline", "tsline_ex",
-        "tsreport", "tsrevar", "tsrline", "tsset", "tssmooth",
-        "tsunab", "ttest", "ttesti", "tut_chk", "tut_wait", "tutorial",
-        "tw", "tware_st", "two", "twoway", "twoway__fpfit_serset",
-        "twoway__function_gen", "twoway__histogram_gen",
-        "twoway__ipoint_serset", "twoway__ipoints_serset",
-        "twoway__kdensity_gen", "twoway__lfit_serset",
-        "twoway__normgen_gen", "twoway__pci_serset",
-        "twoway__qfit_serset", "twoway__scatteri_serset",
-        "twoway__sunflower_gen", "twoway_ksm_serset", "ty", "typ",
-        "type", "typeof", "u", "unab", "unabbrev", "unabcmd",
-        "update", "us", "use", "uselabel", "var", "var_mkcompanion",
-        "var_p", "varbasic", "varfcast", "vargranger", "varirf",
-        "varirf_add", "varirf_cgraph", "varirf_create", "varirf_ctable",
-        "varirf_describe", "varirf_dir", "varirf_drop", "varirf_erase",
-        "varirf_graph", "varirf_ograph", "varirf_rename", "varirf_set",
-        "varirf_table", "varlist", "varlmar", "varnorm", "varsoc",
-        "varstable", "varstable_w", "varstable_w2", "varwle",
-        "vce", "vec", "vec_fevd", "vec_mkphi", "vec_p", "vec_p_w",
-        "vecirf_create", "veclmar", "veclmar_w", "vecnorm",
-        "vecnorm_w", "vecrank", "vecstable", "verinst", "vers",
-        "versi", "versio", "version", "view", "viewsource", "vif",
-        "vwls", "wdatetof", "webdescribe", "webseek", "webuse",
-        "weib1_lf", "weib2_lf", "weib_lf", "weib_lf0 weibhet_glf",
-        "weibhet_glf_sh", "weibhet_glfa", "weibhet_glfa_sh",
-        "weibhet_gp", "weibhet_ilf", "weibhet_ilf_sh", "weibhet_ilfa",
-        "weibhet_ilfa_sh", "weibhet_ip", "weibu_sw", "weibul_p",
-        "weibull", "weibull_c", "weibull_s", "weibullhet",
-        "wh", "whelp", "whi", "which", "whil", "while", "wilc_st",
-        "wilcoxon", "win", "wind", "windo", "window", "winexec",
-        "wntestb", "wntestb_7", "wntestq", "xchart", "xchart_7",
-        "xcorr", "xcorr_7", "xi", "xi_6", "xmlsav", "xmlsave",
-        "xmluse", "xpose", "xsh", "xshe", "xshel", "xshell",
-        "xt_iis", "xt_tis", "xtab_p", "xtabond", "xtbin_p",
-        "xtclog", "xtcloglog", "xtcloglog_8", "xtcloglog_d2",
-        "xtcloglog_pa_p", "xtcloglog_re_p", "xtcnt_p", "xtcorr",
-        "xtdata", "xtdes", "xtfront_p", "xtfrontier", "xtgee",
-        "xtgee_elink", "xtgee_estat", "xtgee_makeivar", "xtgee_p",
-        "xtgee_plink", "xtgls", "xtgls_p", "xthaus", "xthausman",
-        "xtht_p", "xthtaylor", "xtile", "xtint_p", "xtintreg",
-        "xtintreg_8", "xtintreg_d2 xtintreg_p", "xtivp_1",
-        "xtivp_2", "xtivreg", "xtline", "xtline_ex", "xtlogit",
-        "xtlogit_8 xtlogit_d2", "xtlogit_fe_p", "xtlogit_pa_p",
-        "xtlogit_re_p", "xtmixed", "xtmixed_estat", "xtmixed_p",
-        "xtnb_fe", "xtnb_lf", "xtnbreg", "xtnbreg_pa_p",
-        "xtnbreg_refe_p", "xtpcse", "xtpcse_p", "xtpois", "xtpoisson",
-        "xtpoisson_d2", "xtpoisson_pa_p", "xtpoisson_refe_p", "xtpred",
-        "xtprobit", "xtprobit_8", "xtprobit_d2", "xtprobit_re_p",
-        "xtps_fe", "xtps_lf", "xtps_ren", "xtps_ren_8", "xtrar_p",
-        "xtrc", "xtrc_p", "xtrchh", "xtrefe_p", "xtreg", "xtreg_be",
-        "xtreg_fe", "xtreg_ml", "xtreg_pa_p", "xtreg_re",
-        "xtregar", "xtrere_p", "xtset", "xtsf_ll", "xtsf_llti",
-        "xtsum", "xttab", "xttest0", "xttobit", "xttobit_8",
-        "xttobit_p", "xttrans", "yx", "yxview__barlike_draw",
-        "yxview_area_draw", "yxview_bar_draw", "yxview_dot_draw",
-        "yxview_dropline_draw", "yxview_function_draw",
-        "yxview_iarrow_draw", "yxview_ilabels_draw",
-        "yxview_normal_draw", "yxview_pcarrow_draw",
-        "yxview_pcbarrow_draw", "yxview_pccapsym_draw",
-        "yxview_pcscatter_draw", "yxview_pcspike_draw",
-        "yxview_rarea_draw", "yxview_rbar_draw", "yxview_rbarm_draw",
-        "yxview_rcap_draw", "yxview_rcapsym_draw",
-        "yxview_rconnected_draw", "yxview_rline_draw",
-        "yxview_rscatter_draw", "yxview_rspike_draw",
-        "yxview_spike_draw", "yxview_sunflower_draw", "zap_s", "zinb",
-        "zinb_llf", "zinb_plf", "zip", "zip_llf", "zip_p", "zip_plf",
-        "zt_ct_5", "zt_hc_5", "zt_hcd_5", "zt_is_5", "zt_iss_5",
-        "zt_sho_5 zt_smp_5", "ztbase_5", "ztcox_5", "ztdes_5",
-        "ztereg_5", "ztfill_5", "ztgen_5", "ztir_5 ztjoin_5", "ztnb",
-        "ztnb_p", "ztp", "ztp_p", "zts_5", "ztset_5", "ztspli_5",
-        "ztsum_5", "zttoct_5 ztvary_5", "ztweib_5"
-    )
-
-    builtins_functions = (
-        "Cdhms", "Chms", "Clock", "Cmdyhms", "Cofc", "Cofd", "F",
-        "Fden", "Ftail", "I", "J", "_caller", "abbrev", "abs", "acos",
-        "acosh", "asin", "asinh", "atan", "atan2", "atanh",
-        "autocode", "betaden", "binomial", "binomialp", "binomialtail",
-        "binormal", "bofd", "byteorder", "c", "ceil", "char",
-        "chi2", "chi2den", "chi2tail", "cholesky", "chop", "clip",
-        "clock", "cloglog", "cofC", "cofd", "colnumb", "colsof", "comb",
-        "cond", "corr", "cos", "cosh", "d", "daily", "date", "day",
-        "det", "dgammapda", "dgammapdada", "dgammapdadx", "dgammapdx",
-        "dgammapdxdx", "dhms", "diag", "diag0cnt", "digamma",
-        "dofC", "dofb", "dofc", "dofh", "dofm", "dofq", "dofw",
-        "dofy", "dow", "doy", "dunnettprob", "e", "el", "epsdouble",
-        "epsfloat", "exp", "fileexists", "fileread", "filereaderror",
-        "filewrite", "float", "floor", "fmtwidth", "gammaden",
-        "gammap", "gammaptail", "get", "group", "h", "hadamard",
-        "halfyear", "halfyearly", "has_eprop", "hh", "hhC", "hms",
-        "hofd", "hours", "hypergeometric", "hypergeometricp", "ibeta",
-        "ibetatail", "index", "indexnot", "inlist", "inrange", "int",
-        "inv", "invF", "invFtail", "invbinomial", "invbinomialtail",
-        "invchi2", "invchi2tail", "invcloglog", "invdunnettprob",
-        "invgammap", "invgammaptail", "invibeta", "invibetatail",
-        "invlogit", "invnFtail", "invnbinomial", "invnbinomialtail",
-        "invnchi2", "invnchi2tail", "invnibeta", "invnorm", "invnormal",
-        "invnttail", "invpoisson", "invpoissontail", "invsym", "invt",
-        "invttail", "invtukeyprob", "irecode", "issym", "issymmetric",
-        "itrim", "length", "ln", "lnfact", "lnfactorial", "lngamma",
-        "lnnormal", "lnnormalden", "log", "log10", "logit", "lower",
-        "ltrim", "m", "match", "matmissing", "matrix", "matuniform",
-        "max", "maxbyte", "maxdouble", "maxfloat", "maxint", "maxlong",
-        "mdy", "mdyhms", "mi", "mi", "min", "minbyte", "mindouble",
-        "minfloat", "minint", "minlong", "minutes", "missing", "mm",
-        "mmC", "mod", "mofd", "month", "monthly", "mreldif",
-        "msofhours", "msofminutes", "msofseconds", "nF", "nFden",
-        "nFtail", "nbetaden", "nbinomial", "nbinomialp", "nbinomialtail",
-        "nchi2", "nchi2den", "nchi2tail", "nibeta", "norm", "normal",
-        "normalden", "normd", "npnF", "npnchi2", "npnt", "nt", "ntden",
-        "nttail", "nullmat", "plural", "poisson", "poissonp",
-        "poissontail", "proper", "q", "qofd", "quarter", "quarterly",
-        "r", "rbeta", "rbinomial", "rchi2 real", "recode", "regexm",
-        "regexr", "regexs", "reldif", "replay", "return", "reverse",
-        "rgamma", "rhypergeometric", "rnbinomial", "rnormal", "round",
-        "rownumb", "rowsof", "rpoisson", "rt", "rtrim", "runiform", "s",
-        "scalar", "seconds", "sign", "sin", "sinh", "smallestdouble",
-        "soundex", "soundex_nara", "sqrt", "ss", "ssC", "strcat",
-        "strdup", "string", "strlen", "strlower", "strltrim", "strmatch",
-        "strofreal", "strpos", "strproper", "strreverse", "strrtrim",
-        "strtoname", "strtrim", "strupper", "subinstr", "subinword",
-        "substr", "sum", "sweep", "syminv", "t", "tC", "tan", "tanh",
-        "tc", "td", "tden", "th", "tin", "tm", "tq", "trace",
-        "trigamma", "trim", "trunc", "ttail", "tukeyprob", "tw",
-        "twithin", "uniform", "upper", "vec", "vecdiag", "w", "week",
-        "weekly", "wofd", "word", "wordcount", "year", "yearly",
-        "yh", "ym", "yofd", "yq", "yw"
-    )
+    flags = re.MULTILINE | re.DOTALL
 
     tokens = {
         'root': [
             include('comments'),
-            include('vars-strings'),
+            include('strings'),
+            include('macros'),
             include('numbers'),
             include('keywords'),
+            include('operators'),
+            include('format'),
             (r'.', Text),
         ],
-        # Global and local macros; regular and special strings
-        'vars-strings': [
-            (r'\$[a-zA-Z_0-9\{]', Name.Variable.Global, 'var_validglobal'),
-            (r'`[a-zA-Z_0-9]{0,31}\'', Name.Variable),
-            (r'"', String, 'string_dquote'),
-            (r'`"', String, 'string_mquote'),
+        # Comments are a complicated beast in Stata because they can be
+        # nested and there are a few corner cases with that. See:
+        # - github.com/kylebarron/language-stata/issues/90
+        # - statalist.org/forums/forum/general-stata-discussion/general/1448244
+        'comments': [
+            (r'(^//|(?<=\s)//)(?!/)', Comment.Single, 'comments-double-slash'),
+            (r'^\s*\*', Comment.Single, 'comments-star'),
+            (r'/\*', Comment.Multiline, 'comments-block'),
+            (r'(^///|(?<=\s)///)', Comment.Special, 'comments-triple-slash')
+        ],
+        'comments-block': [
+            (r'/\*', Comment.Multiline, '#push'),
+            # this ends and restarts a comment block. but need to catch this so
+            # that it doesn\'t start _another_ level of comment blocks
+            (r'\*/\*', Comment.Multiline),
+            (r'(\*/\s+\*(?!/)[^\n]*)|(\*/)', Comment.Multiline, '#pop'),
+            # Match anything else as a character inside the comment
+            (r'.', Comment.Multiline),
+        ],
+        'comments-star': [
+            (r'///.*?\n', Comment.Single,
+                ('#pop', 'comments-triple-slash')),
+            (r'(^//|(?<=\s)//)(?!/)', Comment.Single,
+                ('#pop', 'comments-double-slash')),
+            (r'/\*', Comment.Multiline, 'comments-block'),
+            (r'.(?=\n)', Comment.Single, '#pop'),
+            (r'.', Comment.Single),
+        ],
+        'comments-triple-slash': [
+            (r'\n', Comment.Special, '#pop'),
+            # A // breaks out of a comment for the rest of the line
+            (r'//.*?(?=\n)', Comment.Single, '#pop'),
+            (r'.', Comment.Special),
+        ],
+        'comments-double-slash': [
+            (r'\n', Text, '#pop'),
+            (r'.', Comment.Single),
         ],
-        # For either string type, highlight macros as macros
-        'string_dquote': [
-            (r'"', String, '#pop'),
-            (r'\\\\|\\"|\\\n', String.Escape),
-            (r'\$', Name.Variable.Global, 'var_validglobal'),
-            (r'`', Name.Variable, 'var_validlocal'),
-            (r'[^$\$`"\\]+', String),
-            (r'[$"\\]', String),
+        # `"compound string"' and regular "string"; note the former are
+        # nested.
+        'strings': [
+            (r'`"', String, 'string-compound'),
+            (r'(?<!`)"', String, 'string-regular'),
         ],
-        'string_mquote': [
+        'string-compound': [
+            (r'`"', String, '#push'),
             (r'"\'', String, '#pop'),
-            (r'\\\\|\\"|\\\n', String.Escape),
-            (r'\$', Name.Variable.Global, 'var_validglobal'),
-            (r'`', Name.Variable, 'var_validlocal'),
-            (r'[^$\$`"\\]+', String),
-            (r'[$"\\]', String),
+            (r'\\\\|\\"|\\\$|\\`|\\\n', String.Escape),
+            include('macros'),
+            (r'.', String)
         ],
-        'var_validglobal': [
-            (r'\{?[a-zA-Z0-9_]{0,32}\}?', Name.Variable.Global, '#pop'),
+        'string-regular': [
+            (r'(")(?!\')|(?=\n)', String, '#pop'),
+            (r'\\\\|\\"|\\\$|\\`|\\\n', String.Escape),
+            include('macros'),
+            (r'.', String)
         ],
-        'var_validlocal': [
-            (r'[a-zA-Z0-9_]{0,31}\'', Name.Variable, '#pop'),
+        # A local is usually
+        #     `\w{0,31}'
+        #     `:extended macro'
+        #     `=expression'
+        #     `[rsen](results)'
+        #     `(++--)scalar(++--)'
+        #
+        # However, there are all sorts of weird rules wrt edge
+        # cases. Instead of writing 27 exceptions, anything inside
+        # `' is a local.
+        #
+        # A global is more restricted, so we do follow rules. Note only
+        # locals explicitly enclosed ${} can be nested.
+        'macros': [
+            (r'\$(\{|(?=[\$`]))', Name.Variable.Global, 'macro-global-nested'),
+            (r'\$', Name.Variable.Global,  'macro-global-name'),
+            (r'`', Name.Variable, 'macro-local'),
         ],
-        # * only OK at line start, // OK anywhere
-        'comments': [
-            (r'^\s*\*.*$', Comment),
-            (r'//.*', Comment.Single),
-            (r'/\*.*?\*/', Comment.Multiline),
-            (r'/[*](.|\n)*?[*]/', Comment.Multiline),
+        'macro-local': [
+            (r'`', Name.Variable, '#push'),
+            (r"'", Name.Variable, '#pop'),
+            (r'\$(\{|(?=[\$`]))', Name.Variable.Global, 'macro-global-nested'),
+            (r'\$', Name.Variable.Global, 'macro-global-name'),
+            (r'.', Name.Variable),  # fallback
+        ],
+        'macro-global-nested': [
+            (r'\$(\{|(?=[\$`]))', Name.Variable.Global, '#push'),
+            (r'\}', Name.Variable.Global, '#pop'),
+            (r'\$', Name.Variable.Global, 'macro-global-name'),
+            (r'`', Name.Variable, 'macro-local'),
+            (r'\w', Name.Variable.Global),  # fallback
+            (r'(?!\w)', Name.Variable.Global, '#pop'),
+        ],
+        'macro-global-name': [
+            (r'\$(\{|(?=[\$`]))', Name.Variable.Global, 'macro-global-nested', '#pop'),
+            (r'\$', Name.Variable.Global, 'macro-global-name', '#pop'),
+            (r'`', Name.Variable, 'macro-local', '#pop'),
+            (r'\w{1,32}', Name.Variable.Global, '#pop'),
         ],
         # Built in functions and statements
         'keywords': [
-            (words(builtins_functions, prefix = r'\b', suffix = r'\('),
+            (words(builtins_functions, prefix = r'\b', suffix = r'(?=\()'),
              Name.Function),
             (words(builtins_base, prefix = r'(^\s*|\s)', suffix = r'\b'),
              Keyword),
@@ -499,9 +164,9 @@ class StataLexer(RegexLexer):
         ],
         # Stata formats
         'format': [
-            (r'%-?\d{1,2}(\.\d{1,2})?[gfe]c?', Name.Variable),
-            (r'%(21x|16H|16L|8H|8L)', Name.Variable),
-            (r'%-?(tc|tC|td|tw|tm|tq|th|ty|tg).{0,32}', Name.Variable),
-            (r'%[-~]?\d{1,4}s', Name.Variable),
+            (r'%-?\d{1,2}(\.\d{1,2})?[gfe]c?', Name.Format),
+            (r'%(21x|16H|16L|8H|8L)', Name.Format),
+            (r'%-?(tc|tC|td|tw|tm|tq|th|ty|tg).{0,32}', Name.Format),
+            (r'%[-~]?\d{1,4}s', Name.Format),
         ]
     }
diff --git a/pygments/styles/__init__.py b/pygments/styles/__init__.py
index 4efd196e..35f64ac5 100644
--- a/pygments/styles/__init__.py
+++ b/pygments/styles/__init__.py
@@ -5,7 +5,7 @@
 
     Contains built-in styles.
 
-    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
+    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
     :license: BSD, see LICENSE for details.
 """
 
@@ -41,7 +41,12 @@ STYLE_MAP = {
     'lovelace': 'lovelace::LovelaceStyle',
     'algol':    'algol::AlgolStyle',
     'algol_nu': 'algol_nu::Algol_NuStyle',
-    'arduino':  'arduino::ArduinoStyle'
+    'arduino':  'arduino::ArduinoStyle',
+    'rainbow_dash': 'rainbow_dash::RainbowDashStyle',
+    'abap':     'abap::AbapStyle',
+    'sas':         'sas::SasStyle',
+    'stata-light': 'stata_light::StataLightStyle',
+    'stata-dark':  'stata_dark::StataDarkStyle',
 }
 
 
diff --git a/pygments/styles/stata.py b/pygments/styles/stata.py
deleted file mode 100644
index 2d8abb7e..00000000
--- a/pygments/styles/stata.py
+++ /dev/null
@@ -1,37 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
-    pygments.styles.stata
-    ~~~~~~~~~~~~~~~~~~~~~
-
-    Style inspired by Stata's do-file editor. Note this is not meant
-    to be a complete style. It's merely meant to mimic Stata's do file
-    editor syntax highlighting.
-"""
-
-from pygments.style import Style
-from pygments.token import Keyword, Name, Comment, String, Error, \
-    Number, Operator, Whitespace
-
-
-class StataStyle(Style):
-    """
-    Style inspired by Stata's do-file editor. Note this is not meant
-    to be a complete style. It's merely meant to mimic Stata's do file
-    editor syntax highlighting.
-    """
-
-    default_style = ''
-
-    styles = {
-        Whitespace:            '#bbbbbb',
-        Comment:               'italic #008800',
-        String:                '#7a2424',
-        Number:                '#2c2cff',
-        Operator:              '',
-        Keyword:               'bold #353580',
-        Keyword.Constant:      '',
-        Name.Function:         '#2c2cff',
-        Name.Variable:         'bold #35baba',
-        Name.Variable.Global:  'bold #b5565e',
-        Error:                 'bg:#e3d2d2 #a61717'
-    }
diff --git a/pygments/styles/stata_dark.py b/pygments/styles/stata_dark.py
new file mode 100644
index 00000000..0d67df0d
--- /dev/null
+++ b/pygments/styles/stata_dark.py
@@ -0,0 +1,40 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.styles.stata_dark
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Dark style inspired by Stata's do-file editor. Note this is not
+    meant to be a complete style, just for Stata's file formats.
+
+    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String, Error, \
+    Number, Operator, Whitespace, Generic, Text
+
+
+class StataDarkStyle(Style):
+
+    default_style = ''
+
+    background_color = "#232629"
+    highlight_color = "#49483e"
+
+    styles = {
+        Whitespace:            '#bbbbbb',
+        Error:                 'bg:#e3d2d2 #a61717',
+        Text:                  '#cccccc',
+        String:                '#51cc99',
+        Number:                '#4FB8CC',
+        Operator:              '',
+        Name.Function:         '#6a6aff',
+        Name.Format:           '#e2828e',
+        Keyword:               'bold #7686bb',
+        Keyword.Constant:      '',
+        Comment:               'italic #777777',
+        Name.Variable:         'bold #7AB4DB',
+        Name.Variable.Global:  'bold #BE646C',
+        Generic.Prompt:        '#ffffff',
+    }
diff --git a/pygments/styles/stata_light.py b/pygments/styles/stata_light.py
new file mode 100644
index 00000000..86802ef7
--- /dev/null
+++ b/pygments/styles/stata_light.py
@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+"""
+    pygments.styles.stata_light
+    ~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Light Style inspired by Stata's do-file editor. Note this is not
+    meant to be a complete style, just for Stata's file formats.
+
+    :copyright: Copyright 2006-2017 by the Pygments team, see AUTHORS.
+    :license: BSD, see LICENSE for details.
+"""
+
+from pygments.style import Style
+from pygments.token import Keyword, Name, Comment, String, Error, \
+    Number, Operator, Whitespace, Text
+
+
+class StataLightStyle(Style):
+    """
+    Light mode style inspired by Stata's do-file editor. This is not
+    meant to be a complete style, just for use with Stata.
+    """
+
+    default_style = ''
+    styles = {
+        Text:                  '#111111',
+        Whitespace:            '#bbbbbb',
+        Error:                 'bg:#e3d2d2 #a61717',
+        String:                '#7a2424',
+        Number:                '#2c2cff',
+        Operator:              '',
+        Name.Function:         '#2c2cff',
+        Name.Format:           '#be646c',
+        Keyword:               'bold #353580',
+        Keyword.Constant:      '',
+        Comment:               'italic #008800',
+        Name.Variable:         'bold #35baba',
+        Name.Variable.Global:  'bold #b5565e',
+    }