0.7.3 start to look at document harvest (initial stub)

7 files changed, 170 insertions, 174 deletions

diff --git a/src/doc_reform/meta/conf_make_meta_json.d b/src/doc_reform/meta/conf_make_meta_json.d
index fcd52c1..5fd4499 100644
--- a/src/doc_reform/meta/conf_make_meta_json.d
+++ b/src/doc_reform/meta/conf_make_meta_json.d
@@ -5,6 +5,8 @@
 module doc_reform.meta.conf_make_meta_json;
 static template contentJSONtoDocReformStruct() {
   import
+    std.algorithm,
+    std.array,
     std.exception,
     std.regex,
     std.stdio,
@@ -16,6 +18,7 @@ static template contentJSONtoDocReformStruct() {
   import
     doc_reform.meta.conf_make_meta_structs,
     doc_reform.meta.conf_make_meta_json,
+    doc_reform.meta.defaults,
     doc_reform.meta.rgx;
   ConfCompositePlus _struct_composite;
   auto contentJSONtoDocReformStruct(C,J)(C _struct_composite, J _json, string _identifier) {
@@ -361,6 +364,108 @@ static template contentJSONtoDocReformStruct() {
       }
     }
     /+ meta ------------------------------------------------------------------- +/
+    if (_struct_composite.meta.creator_author.empty) {
+      if ("creator" in _json.object) {
+        if ("author" in _json.object["creator"]
+          && (_json.object["creator"]["author"].type().to!string == "string")
+        ) {
+          _struct_composite.meta.creator_author = _json.object["creator"]["author"].str;
+        }
+        if ("email" in _json.object["creator"]
+          && (_json.object["creator"]["email"].type().to!string == "string")
+        ) {
+          _struct_composite.meta.creator_author_email = _json.object["creator"]["email"].str;
+        }
+        if ("illustrator" in _json.object["creator"]
+          && (_json.object["creator"]["illustrator"].type().to!string == "string")
+        ) {
+          _struct_composite.meta.creator_illustrator = _json.object["creator"]["illustrator"].str;
+        }
+        if ("translator" in _json.object["creator"]
+          && (_json.object["creator"]["translator"].type().to!string == "string")
+        ) {
+          _struct_composite.meta.creator_translator = _json.object["creator"]["translator"].str;
+        }
+      }
+      string[] authors_arr;
+      string[][string] authors_hash_arr = [ "first" : [], "last" : [], "full" : [], "last_first" : [], "as_input" : [] ];
+      string[] authors_raw_arr
+        = _struct_composite.meta.creator_author.split(rgx.arr_delimiter);
+      auto _lastname = appender!(char[])();
+      foreach (author_raw; authors_raw_arr) {
+        authors_arr                  ~= author_raw.replace(rgx.raw_author_munge, "$2 $1");
+        authors_hash_arr["first"]    ~= author_raw.replace(rgx.raw_author_munge, "$2");
+        authors_hash_arr["last"]     ~= author_raw.replace(rgx.raw_author_munge, "$1");
+        authors_hash_arr["full"]     ~= author_raw.replace(rgx.raw_author_munge, "$2 $1");
+        authors_hash_arr["as_input"] ~= author_raw;
+        if (auto m = author_raw.match(rgx.raw_author_munge)) {
+          (m.captures[1]).map!toUpper.copy(_lastname);
+          authors_hash_arr["last_first"] ~= _lastname.data.to!string ~ ", " ~ m.captures[2];
+          _lastname = appender!(char[])();
+        }
+      }
+      _struct_composite.meta.creator_author     = authors_arr.join(", ").chomp.chomp;
+      string _author_name_last_first = authors_hash_arr["last_first"].join("; ").chomp.chomp;
+      _struct_composite.meta.creator_author_surname_fn = (_author_name_last_first.length > 0)
+      ? _author_name_last_first
+      : authors_hash_arr["as_input"].join("; ").chomp.chomp;
+    }
+    if (_struct_composite.meta.title_main.empty) {
+      if ("title" in _json.object) {
+        if ((_json.object["title"].type().to!string) == "string") {
+          _struct_composite.meta.title_main = _json.object["title"].str;
+        } else {
+          if ("edition" in _json.object["title"]
+            && (_json.object["title"]["edition"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_edition = _json.object["title"]["edition"].str;
+          }
+          if ("full" in _json.object["title"]
+            && (_json.object["title"]["full"].type().to!string == "string")
+          ) {}
+          if ("language" in _json.object["title"]
+            && (_json.object["title"]["language"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_language = _json.object["title"]["language"].str;
+          }
+          if ("main" in _json.object["title"]
+            && (_json.object["title"]["main"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_main = _json.object["title"]["main"].str;
+          } else if ("title" in _json.object["title"]
+            && (_json.object["title"]["title"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_main = _json.object["title"]["title"].str;
+          }
+          if ("note" in _json.object["title"]
+            && (_json.object["title"]["note"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_note = _json.object["title"]["note"].str;
+          }
+          if ("sub" in _json.object["title"]
+            && (_json.object["title"]["sub"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_sub = _json.object["title"]["sub"].str;
+          }
+          if ("subtitle" in _json.object["title"]
+            && (_json.object["title"]["subtitle"].type().to!string == "string")
+          ) {
+            _struct_composite.meta.title_subtitle = _json.object["title"]["subtitle"].str;
+          }
+        }
+      }
+      if ((!(_struct_composite.meta.title_subtitle.empty))
+      && (_struct_composite.meta.title_sub.empty)) {
+        _struct_composite.meta.title_sub = _struct_composite.meta.title_subtitle;
+      }
+      _struct_composite.meta.title_full = (_struct_composite.meta.title_sub.empty)
+      ? _struct_composite.meta.title_main
+      : format(
+          "%s - %s",
+          _struct_composite.meta.title_main,
+          _struct_composite.meta.title_sub,
+        );
+    }
     if ("classify" in _json.object) {
       if ("dewey" in _json.object["classify"]
         && (_json.object["classify"]["dewey"].type().to!string == "string")
@@ -386,6 +491,22 @@ static template contentJSONtoDocReformStruct() {
         && (_json.object["classify"]["topic_register"].type().to!string == "string")
       ) {
         _struct_composite.meta.classify_topic_register = _json.object["classify"]["topic_register"].str;
+        string[] main_topics_ = _struct_composite.meta.classify_topic_register.split(rgx.topic_register_main_terms_split);
+        string[] topics;
+        string   topics_tmp;
+        string[] multiple_sub_terms;
+        foreach (mt; main_topics_) {
+          topics_tmp = mt.replaceAll(rgx.topic_register_main_term_plus_rest_split,    mkup.sep);
+          if (auto m = topics_tmp.match(rgx.topic_register_multiple_sub_terms_split)) {
+            multiple_sub_terms = m.captures[1].split(rgx.topic_register_sub_terms_split);
+            foreach (subterm; multiple_sub_terms) {
+              topics ~= m.captures.pre ~ mkup.sep ~ subterm;
+            }
+          } else {
+            topics ~= topics_tmp;
+          }
+        }
+        _struct_composite.meta.classify_topic_register_arr = topics;
       }
     }
     if ("date" in _json.object) {
@@ -424,6 +545,13 @@ static template contentJSONtoDocReformStruct() {
       ) {
         _struct_composite.meta.date_valid = _json.object["date"]["valid"].str;
       }
+      _struct_composite.meta.author_date_title = format(
+        "%s %s \"%s\"",
+        _struct_composite.meta.creator_author_surname_fn,
+        (_struct_composite.meta.date_published.length > 0)
+          ? "(" ~ _struct_composite.meta.date_published ~ ")" : "",
+        _struct_composite.meta.title_full,
+      );
     }
     if ("links" in _json.object) {}
     if ("notes" in _json.object) {
@@ -508,93 +636,6 @@ static template contentJSONtoDocReformStruct() {
         _struct_composite.meta.rights_license = _json.object["rights"]["license"].str;
       }
     }
-    if (_struct_composite.meta.creator_author.empty) {
-      if ("creator" in _json.object) {
-        if ("author" in _json.object["creator"]
-          && (_json.object["creator"]["author"].type().to!string == "string")
-        ) {
-          _struct_composite.meta.creator_author = _json.object["creator"]["author"].str;
-        }
-        if ("email" in _json.object["creator"]
-          && (_json.object["creator"]["email"].type().to!string == "string")
-        ) {
-          _struct_composite.meta.creator_author_email = _json.object["creator"]["email"].str;
-        }
-        if ("illustrator" in _json.object["creator"]
-          && (_json.object["creator"]["illustrator"].type().to!string == "string")
-        ) {
-          _struct_composite.meta.creator_illustrator = _json.object["creator"]["illustrator"].str;
-        }
-        if ("translator" in _json.object["creator"]
-          && (_json.object["creator"]["translator"].type().to!string == "string")
-        ) {
-          _struct_composite.meta.creator_translator = _json.object["creator"]["translator"].str;
-        }
-      }
-      string[] authors_arr;
-      string[] authors_raw_arr
-        = _struct_composite.meta.creator_author.split(rgx.arr_delimiter);
-      foreach (author_raw; authors_raw_arr) {
-        authors_arr ~= author_raw.replace(rgx.raw_author_munge, "$2 $1");
-      }
-      _struct_composite.meta.creator_author = join(authors_arr, ", ").chomp.chomp;
-    }
-    if (_struct_composite.meta.title_main.empty) {
-      if ("title" in _json.object) {
-        if ((_json.object["title"].type().to!string) == "string") {
-          _struct_composite.meta.title_main = _json.object["title"].str;
-        } else {
-          if ("edition" in _json.object["title"]
-            && (_json.object["title"]["edition"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_edition = _json.object["title"]["edition"].str;
-          }
-          if ("full" in _json.object["title"]
-            && (_json.object["title"]["full"].type().to!string == "string")
-          ) {}
-          if ("language" in _json.object["title"]
-            && (_json.object["title"]["language"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_language = _json.object["title"]["language"].str;
-          }
-          if ("main" in _json.object["title"]
-            && (_json.object["title"]["main"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_main = _json.object["title"]["main"].str;
-          } else if ("title" in _json.object["title"]
-            && (_json.object["title"]["title"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_main = _json.object["title"]["title"].str;
-          }
-          if ("note" in _json.object["title"]
-            && (_json.object["title"]["note"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_note = _json.object["title"]["note"].str;
-          }
-          if ("sub" in _json.object["title"]
-            && (_json.object["title"]["sub"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_sub = _json.object["title"]["sub"].str;
-          }
-          if ("subtitle" in _json.object["title"]
-            && (_json.object["title"]["subtitle"].type().to!string == "string")
-          ) {
-            _struct_composite.meta.title_subtitle = _json.object["title"]["subtitle"].str;
-          }
-        }
-      }
-      if ((!(_struct_composite.meta.title_subtitle.empty))
-      && (_struct_composite.meta.title_sub.empty)) {
-        _struct_composite.meta.title_sub = _struct_composite.meta.title_subtitle;
-      }
-      _struct_composite.meta.title_full = (_struct_composite.meta.title_sub.empty)
-      ? _struct_composite.meta.title_main
-      : format(
-          "%s - %s",
-          _struct_composite.meta.title_main,
-          _struct_composite.meta.title_sub,
-        );
-    }
     return _struct_composite;
   }
 }
diff --git a/src/doc_reform/meta/conf_make_meta_structs.d b/src/doc_reform/meta/conf_make_meta_structs.d
index 874e509..ff1ec76 100644
--- a/src/doc_reform/meta/conf_make_meta_structs.d
+++ b/src/doc_reform/meta/conf_make_meta_structs.d
@@ -181,7 +181,9 @@ struct MetaComposite {
   string   classify_loc;
   string   classify_subject;
   string   classify_topic_register;
+  string[] classify_topic_register_arr;
   string   creator_author;
+  string   creator_author_surname_fn;
   string   creator_author_email;
   string   creator_illustrator;
   string   creator_translator;
@@ -223,6 +225,7 @@ struct MetaComposite {
   string   title_short;
   string   title_sub;
   string   title_subtitle;
+  string   author_date_title;
 }
 struct ConfComposite {
   MetaComposite               meta;
diff --git a/src/doc_reform/meta/metadoc.d b/src/doc_reform/meta/metadoc.d
index d8cc19f..a4b920b 100644
--- a/src/doc_reform/meta/metadoc.d
+++ b/src/doc_reform/meta/metadoc.d
@@ -9,6 +9,7 @@ template DocReformAbstraction() {
   import
     doc_reform.meta,
     doc_reform.meta.metadoc_summary,
+    doc_reform.meta.metadoc_harvest,
     doc_reform.meta.metadoc_from_src,
     doc_reform.meta.conf_make_meta_structs,
     doc_reform.meta.conf_make_meta_toml,
diff --git a/src/doc_reform/meta/metadoc_harvest.d b/src/doc_reform/meta/metadoc_harvest.d
new file mode 100644
index 0000000..c3534f9
--- /dev/null
+++ b/src/doc_reform/meta/metadoc_harvest.d
@@ -0,0 +1,30 @@
+module doc_reform.meta.metadoc_harvest;
+template DocReformMetaDocHarvest() {
+  auto DocReformMetaDocHarvest(T,H)(
+    T  doc_matters,
+    H  harvest,
+  ) {
+    import
+      doc_reform.meta.defaults,
+      doc_reform.meta.rgx;
+    import
+      std.array,
+      std.exception,
+      std.regex,
+      std.stdio,
+      std.string,
+      std.traits,
+      std.typecons,
+      std.uni,
+      std.utf,
+      std.conv : to;
+    mixin InternalMarkup;
+    auto markup = InlineMarkup();
+    harvest.title              = doc_matters.conf_make_meta.meta.title_full;
+    harvest.author             = doc_matters.conf_make_meta.meta.creator_author;
+    harvest.author_date_title  = doc_matters.conf_make_meta.meta.author_date_title;
+    harvest.date_published     = doc_matters.conf_make_meta.meta.date_published;
+    harvest.topic_register_arr = doc_matters.conf_make_meta.meta.classify_topic_register_arr;
+    return harvest;
+  }
+}
diff --git a/src/doc_reform/meta/metadoc_summary.d b/src/doc_reform/meta/metadoc_summary.d
index 768cebd..4beada8 100644
--- a/src/doc_reform/meta/metadoc_summary.d
+++ b/src/doc_reform/meta/metadoc_summary.d
@@ -1,6 +1,6 @@
 module doc_reform.meta.metadoc_summary;
-template DocReformAbstractionSummary() {
-  void DocReformAbstractionSummary(S,T)(
+template DocReformMetaDocSummary() {
+  void DocReformMetaDocSummary(S,T)(
     const S  doc_abstraction,
           T  doc_matters,
   ) {
diff --git a/src/doc_reform/meta/metadochead.d b/src/doc_reform/meta/metadochead.d
deleted file mode 100644
index 05be0a8..0000000
--- a/src/doc_reform/meta/metadochead.d
+++ /dev/null
@@ -1,84 +0,0 @@
-module doc_reform.meta.metadochead;
-template DocReformHarvestGetFromHead() { // TODO
-  import
-    std.datetime,
-    std.getopt,
-    std.file,
-    std.path,
-    std.process;
-  import
-    doc_reform.meta,
-    doc_reform.meta.metadoc_summary,
-    doc_reform.meta.metadoc_from_src,
-    doc_reform.meta.conf_make_meta_structs,
-    doc_reform.meta.conf_make_meta_toml,
-    doc_reform.meta.conf_make_meta_json,
-    doc_reform.meta.defaults,
-    doc_reform.meta.doc_debugs,
-    doc_reform.meta.rgx,
-    doc_reform.source.paths_source,
-    doc_reform.source.read_config_files,
-    doc_reform.source.read_source_files,
-    doc_reform.output.hub;
-  mixin DocReformRgxInit;
-  mixin contentJSONtoDocReformStruct;
-  mixin DocReformBiblio;
-  mixin DocReformRgxInitFlags;
-  mixin outputHub;
-  enum headBody { header, body_content, insert_file_list, image_list }
-  enum makeMeta { make, meta }
-  static auto rgx = Rgx();
-  auto DocReformHarvestGetFromHead(E,O,M)( // TODO
-    E _env,
-    O _opt_action,
-    M _manifest
-  ){
-    auto _config_document_struct = readConfigDoc!()(_manifest, _env);    // document config file
-    auto _config_local_site_struct = readConfigSite!()(_manifest, _env); // local site config
-    ConfCompositePlus _make_and_meta_struct;
-    _make_and_meta_struct = configParseTOMLreturnDocReformStruct!()(_make_and_meta_struct, _config_document_struct);
-    _make_and_meta_struct = configParseTOMLreturnDocReformStruct!()(_make_and_meta_struct, _config_local_site_struct);
-    /+ ↓ read file (filename with path) +/
-    /+ ↓ file tuple of header and content +/
-    if ((_opt_action.debug_do)
-    || (_opt_action.very_verbose)
-    ) {
-      writeln("step1 commence → (get document header & body & insert file list & if needed image list)"
-      );
-    }
-    auto _header_body_insertfilelist_imagelist
-      = DocReformRawMarkupContent!()(_opt_action, _manifest.src.path_and_fn);
-    static assert(!isTypeTuple!(_header_body_insertfilelist_imagelist));
-    static assert(_header_body_insertfilelist_imagelist.length==4);
-    if ((_opt_action.debug_do)
-    || (_opt_action.very_verbose)
-    ) {
-      writeln("- step1 complete");
-    }
-    debug(header_and_body) {
-      writeln(header);
-      writeln(_header_body_insertfilelist_imagelist.length);
-      writeln(_header_body_insertfilelist_imagelist.length[headBody.body_content][0]);
-    }
-    /+ ↓ split header into make and meta +/
-    if ((_opt_action.debug_do)
-    || (_opt_action.very_verbose)
-    ) {
-      writeln("step2 commence → (read document header - toml, return struct)");
-    }
-    _make_and_meta_struct =
-    docHeaderMakeAndMetaTupTomlExtractAndConvertToStruct!()(
-      _make_and_meta_struct,
-      _header_body_insertfilelist_imagelist[headBody.header]
-    );
-    if ((_opt_action.debug_do)
-    || (_opt_action.very_verbose)
-    ) {
-      writeln("- step2 complete");
-    }
-    
-    auto t = tuple(doc_matters_shared, doc_matters_abridged_collected);
-    static assert(t.length==2);
-    return t;
-  }
-}
diff --git a/src/doc_reform/meta/rgx.d b/src/doc_reform/meta/rgx.d
index 373400f..544b432 100644
--- a/src/doc_reform/meta/rgx.d
+++ b/src/doc_reform/meta/rgx.d
@@ -7,6 +7,7 @@ static template DocReformRgxInit() {
   static struct Rgx {
     /+ misc +/
     static true_dollar                                    = ctRegex!(`\$`, "gm");
+    static sep                                            = ctRegex!(`␣`, "gm");
     static flag_action                                    = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
     static flag_action_str                                = ctRegex!(` (--[a-z][a-z0-9-]+)`);
     static within_quotes                                  = ctRegex!(`"(.+?)"`, "m");
@@ -43,7 +44,7 @@ static template DocReformRgxInit() {
     /+ header +/
     static variable_doc_title                             = ctRegex!(`@title`);
     static variable_doc_author                            = ctRegex!(`@author|@creator`);
-    static raw_author_munge                               = ctRegex!(`(\S.+?),\s+(.+)`,"i");
+    static raw_author_munge                               = ctRegex!(`(?P<last>\S.+?),\s+(?P<first>.+)`,"i");
     static toml_header_meta_title                         = ctRegex!(`^\s*(title\s*=\s*"|\[title\])`, "m");
     /+ heading & paragraph operators +/
     static heading_a                                      = ctRegex!(`^:?[A][~] `, "m");
@@ -191,6 +192,10 @@ static template DocReformRgxInit() {
     static bi_main_term_plus_rest_split                   = ctRegex!(`\s*:\s*`);
     static bi_sub_terms_plus_object_number_offset_split   = ctRegex!(`\s*\|\s*`);
     static bi_term_and_object_numbers_match               = ctRegex!(`^(.+?)\+(\d+)`);
+    static topic_register_main_terms_split                = ctRegex!(`\s*;\s*`);
+    static topic_register_main_term_plus_rest_split       = ctRegex!(`\s*:\s*`);
+    static topic_register_sub_terms_split                 = ctRegex!(`\s*\|\s*`);
+    static topic_register_multiple_sub_terms_split        = ctRegex!(`␣([^|␣]+(?:\|[^|␣]+)+)`);
     /+ language codes +/
     auto language_codes                                    =
        ctRegex!("(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)");