# # Example config file for ht://Dig. # # This configuration file is used by all the programs that make up ht://Dig. # Please refer to the attribute reference manual for more details on what # can be put into this file. (http://www.htdig.org/confindex.html) # Note that most attributes have very reasonable default values so you # really only have to add attributes here if you want to change the defaults. # # What follows are some of the common attributes you might want to change. # # # Specify where the database files need to go. Make sure that there is # plenty of free disk space available for the databases. They can get # pretty big. # database_dir: /var/www/htdig/dborigin # # This specifies the URL where the robot (htdig) will start. You can specify # multiple URLs here. Just separate them by some whitespace. # The example here will cause the ht://Dig homepage and related pages to be # indexed. # You could also index all the URLs in a file like so: # start_url: `${common_dir}/start.url` # start_url: start_url: http://www.ch.ic.ac.uk/chemime/ # # This attribute limits the scope of the indexing process. The default is to # set it to the same as the start_url above. This way only pages that are on # the sites specified in the start_url attribute will be indexed and it will # reject any URLs that go outside of those sites. # # Keep in mind that the value for this attribute is just a list of string # patterns. As long as URLs contain at least one of the patterns it will be # seen as part of the scope of the index. # limit_urls_to: ${start_url} # ${start_url} # # If there are particular pages that you definately do NOT want to index, you # can use the exclude_urls attribute. The value is a list of string patterns. # If a URL matches any of the patterns, it will NOT be indexed. This is # useful to exclude things like virtual web trees or database accesses. By # default, all CGI URLs will be excluded. (Note that the /cgi-bin/ convention # may not work on your web server. Check the path prefix used on your web # server.) # exclude_urls: /cgi-bin/ .cgi # # The string htdig will send in every request to identify the robot. Change # this to your email address. # maintainer: rzepa@ic.ac.uk # # The excerpts that are displayed in long results rely on stored information # in the index databases. The compiled default only stores 512 characters of # text from each document (this excludes any HTML markup...) If you plan on # using the excerpts you probably want to make this larger. The only concern # here is that more disk space is going to be needed to store the additional # information. Since disk space is cheap (! :-)) you might want to set this # to a value so that a large percentage of the documents that you are going # to be indexing are stored completely in the database. At SDSU we found # that by setting this value to about 50k the index would get 97% of all # documents completely and only 3% was cut off at 50k. You probably want to # experiment with this value. # Note that if you want to set this value low, you probably want to set the # excerpt_show_top attribute to false so that the top excerpt_length characters # of the document are always shown. # max_head_length: 10000 # # To limit network connections, ht://Dig will only pull up to a certain limit # of bytes. This prevents the indexing from dying because the server keeps # sending information. However, several FAQs happen because people have files # bigger than the default limit of 100KB. This sets the default a bit higher. # (see for more) # max_doc_size: 2000000 # # Depending on your needs, you might want to enable some of the fuzzy search # algorithms. There are several to choose from and you can use them in any # combination you feel comfortable with. Each algorithm will get a weight # assigned to it so that in combinations of algorithms, certain algorithms get # preference over others. Note that the weights only affect the ranking of # the results, not the actual searching. # The available algorithms are: # exact # endings # synonyms # soundex # metaphone # By default only the "exact" algorithm is used with weight 1. # Note that if you are going to use any of the algorithms other than "exact", # you need to use the htfuzzy program to generate the databases that each # algorithm requires. # search_algorithm: exact:1 synonyms:0.5 endings:0.1 # #External parsers #pdf_parser: /usr/adobe/Acrobat4.0/bin/acroread -toPostScript -pairs external_parsers: chemical/x-pdb "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-jcamp-dx "/usr/java/bin/java chemical.Htdigfront" \ x-world/x-vrml "/usr/java/bin/java chemical.Htdigfront" \ model/x-vrml "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-gaussian-input "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-gaussian-cube "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mopac-input "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mdl-molfile "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-xyz "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mdl-rxnfile "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mdl-sdfile "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mdl-rdfile "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mdl-tgf "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-genbank "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-alchemy "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-ncbi-asn1 "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-chem3d "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-cdx "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-cif "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-cmdf "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-cml "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-csml "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-cxf "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-embl-dl-nucleotide "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-gaussian-checkpoint "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mopac-graph "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-gamess "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-isostar "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-kinemage "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-macmolecule "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mif "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mmcif "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-macromolecule-input "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mol2 "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-jjc-review-surface "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-daylight-smiles "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-galactic-spc "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-swissprot "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-ncbi-asn1-binary "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-jjc-review-vib "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-vmd "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-vamas-iso14976 "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-jjc-review-xyz "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-gamess "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-vamas-iso14976 "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-gcg8-sequence "/usr/java/bin/java chemical.Htdigfront" \ chemical/ncbi-asn1-binary "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-macromodel-input "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mmcif "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-cache-csf "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-crossfire "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-mdl-base "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-chemdraw "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-macgamess-log "/usr/java/bin/java chemical.Htdigfront" \ chemical/x-macgamess "/usr/java/bin/java chemical.Htdigfront" #meta tags # default is false use_meta_description: true # #the defined meta tags # keywords_meta_tag_names : DC-CHEM.substance DC-CHEM.coordinates \ DC-CHEM.computation-simulation DC-CHEM.biological-activity DC-CHEM.safety \ DC-CHEM.synthesis DC-CHEM.characterisation DC-CHEM.reaction-data \ DC-CHEM.smiles DC.Title DC.Publisher DC.Date DC.title DC.subject \ DC.description generator keywords descripton # weighting given to metadata element # meta_description_factor: 10 # #Defines the metadata element length # max_meta_description_length: 10000 # #Sets the title weigh # title_factor: 10 # # Keywords weighting # keyword_factor: 10 # # Weights for headings # heading_factor_1: 5 heading_factor_2: 4 heading_factor_3: 3 heading_factor_4: 1 heading_factor_5: 1 heading_factor_6: 0 # # allow numbers to be part of a search # allow_numbers: true # #Number of stars the search forms can display # max_stars: 10 # # The following are the templates used in the builtin search results # The default is to use compiled versions of these files, which produces # slightly faster results. However, uncommenting these lines makes it # very easy to change the format of search results. # See no_next_page_text: prev_page_text: prev no_prev_page_text: page_number_text: "1" \ "2" \ "3" \ "4" \ "5" \ "6" \ "7" \ "8" \ "9" \ "10" # # To make the current page stand out, we will put a border arround the # image for that page. # no_page_number_text: "1" \ "2" \ "3" \ "4" \ "5" \ "6" \ "7" \ "8" \ "9" \ "10" # local variables: # mode: text # eval: (if (eq window-system 'x) (progn (setq font-lock-keywords (list '("^#.*" . font-lock-keyword-face) '("^[a-zA-Z][^ :]+" . font-lock-function-name-face) '("[+$]*:" . font-lock-comment-face) )) (font-lock-mode))) # end: